Wake-word detection suppression

WAKE-WORD DETECTION SUPPRESSION

[0001] This application claims priority to U.S. Patent Application No. 15/670,361, filed August

7,2017.

FIELD OF THE DISCLOSURE

[0002] The disclosure is related to consumer goods and, more particularly, to methods, systems, products, features, services, and other elements directed to media playback or some aspect thereof.

BACKGROUND

[0003] Options for accessing and listening to digital audio in an out-loud setting were limited until in 2003, when SONOS, Inc. filed for one of its first patent applications, entitled Method for Synchronizing Audio Playback between Multiple Networked Devices, and began offering a media playback system for sale in 2005. The Sonos Wireless HiFi System enables people to experience music from many sources via one or more networked playback devices. Through a software control application installed on a smartphone, tablet, or computer, one can play what he or she wants in any room that has a networked playback device. Additionally, using the controller, for example, different songs can be streamed to each room with a playback device, rooms can be grouped together for synchronous playback, or the same song can be heard in all rooms synchronously.

[0004] Given the ever growing interest in digital media, there continues to be a need to develop consumer-accessible technologies to further enhance the listening experience.

[0004a] One example aspect ofthe present disclosure is directed to a method for a playback device, the method comprising : receiving, via a network interface of the playback device, data representing audio contant for playback by the playback device; and before the audio content is played back by the playback device, detecting, in the audio content, one or more wake words for one or more voice services; determining that the one or more networked microphone devices are within an audible vicinity of the playback device; in response to determining that the one or more networked microphones are in audible vicinity of the audio content, causing the one or more networked microphone devices determined to be within the audible range of the playback device to disable its respective wake response to the detected one or more wake words during playback of the audio content by the playback device, wherein, when enabled, the wake response of a given networked microphone

Date reçue / Date received 2021-11-29 device to a particular wake word causes the given network microphone device to listen, via a microphone, for a voice command following the particular wake word; and playing back the audio content via one or more speakers of the playback device.

[0004b] Another example aspect of the present disclosure is directed to a playback device comprising a network interface, one or more microphones, one or more processors, data storage having stored therein instructions executable by the one or more processors to cause the playback device to perform functions comprising: receiving audio content for playback by the playback device; providing a sound data stream representing the received audio content to (i) a voice assistant service (VAS) wake-word engine and (ii) a local keyword engine, wherein the VAS wake-word engine is operable to (a) generate a VAS wake word response when die VAS wake-word engine detects a VAS wake word in a microphone sound data stream representing sound detected by one or more microphones of the playback device and (b) stream sound data representing the sound detected by the one or more microphones to one or more servers of the VAS when the VAS wake word response is generated, and wherein the local keyword engine is operable to (a) generate a local keyword response when the local keyword engine detects one or more local keywords in the microphone sound data stream representing sound detected by the one or more microphones and (b) determine an intent of a voice input comprising the one or more local keywords when the local keyword response is generated; playing back a first portion of the audio content via one or more speakers; detecting, via the local keyword engine, that a second portion of the received audio content includes sound data matching one or more particular local keywords; before tire second portion of the received audio content that includes the sound data matching the one or more particular local keywords is played back, disabling the local keyword response of the local keyword engine to the one or more particular local keywords during playback of the second portion of the audio content by the playback device; and playing back the second portion of the audio content via one or more speakers.

[0004c] Another example aspect of tire present disclosure is directed to a method to be performed by a playback device, the method comprising: receiving audio content for playback by the playback device; providing a sound data stream representing the received audio content to (i) a voice assistant service (VAS) wake-word engine and (ii) a local keyword engine, wherein tire VAS wake-word engine is operable to (a) generate a VAS wake word response when the VAS wake-word engine detects a VAS wake word in a microphone sound data stream representing sound detected by one or more microphones of the playback device and (b) stream sound data representing the sound detected by the one or more microphones to one or more servers of the VAS when the VAS wake word response is 2

Date reçue / Date received 2021-11-29 generated, and wherein the local keyword engine is operable to (a) generate a local keyword response when the local keyword engine detects one or more local keywords in the microphone sound data stream representing sound detected by the one or more microphones and (b) determine an intent of a voice input comprising the one or more local keywords when the local keyword response is generated; playing back a first portion of the audio content via one or more speakers; detecting, via the local keyword angine, that a second portion of the received audio content includes sound data matching one or more particular local keywords; before die second portion of the received audio content that includes the sound data matching the one or more particular local keywords is played back, disabling the local keyword response of the local keyword engine to the one or more particular local keywords during playback of the second portion of the audio content by the playback device; and playing back the second portion of the audio content via one or more speakers.

[0004d] Another example aspect of the present disclosure is directed to a tangible, non-transitory computer-readable medium having instructions stored thereon that, when executed by one or more processors of a playback device, cause die playback device to perform functions comprising: receiving audio content for playback by the playback device; providing a sound data stream representing the received audio content to (i) a voice assistant service (VAS) wake-word engine and (ii) a local keyword engine, wherein the VAS wake-word engine is operable to (a) generate a VAS wake word response when the VAS wake-word engine detects a VAS wake word in a microphone sound data stream representing sound detected by one or more microphones of the playback device and (b) stream sound data representing the sound detected by the one or more microphones to one or more servers of the VAS when the VAS wake word response is generated, and wherein the local keyword engine is operable to (a) generate a local keyword response when the local keyword engine detects one or more local keywords in the microphone sound data stream representing sound detected by ihe one or more microphones and (b) determine an intent of a voice input comprising the one or more local keywords when the local keyword response is generated; playing back a first portion of the audio content via one or more speakers; detecting, via the local keyword engine, that a second portion of the received audio content includes sound data matching one or more particular local keywords; before the second portion of the received audio content that includes the sound data matching the one or more particular local keywords is played back, disabling the local keyword response of the local keyword engine to the one or more particular local keywords during playback of the second portion of the audio content by the playback device; and playing back the second portion of the audio content via one or more speakers.

Date reçue / Date received 2021-11-29

[0004e] Yet another aspect of the present disclosure is directed to a playback device comprising: a network interface; one or more microphones; one or more processors; data storage having stored therein instructions executable by the one or more processors to cause the playback device to perform functions comprising: receiving audio content for playback by the playback device; providing a sound data stream representing the received audio content to (i) a voice assistant service (VAS) wake-word engine and (ii) a local wakeword engine, wherein the VAS wake-word engine is operable to (a) generate a VAS wake word response when the VAS wake-word engine detects a VAS wake word in a microphone sound data stream representing sound detected by one or more microphones of the playback device and (b) stream sound data representing the sound detected by the one or more microphones to one or more servers of the VAS when the VAS wake word response is generated, and wherein the local wakeword engine is operable to (a) generate a local wakeword response when the local wakeword engine detects one or more local wakewords in the microphone sound data stream representing sound detected by the one or more microphones and (b) determine an intent of a voice input comprising the one or more local wakewords when the local wakeword response is generated; playing back a first portion of the audio content via one or more speakers; detecting, via the local wakeword engine, that a second portion of the received audio content includes sound data matching one or more particular local wakewords; before the second portion of die received audio content that includes the sound data matching the one or more particular local wakewords is played back, disabling the local wakeword response of die local wakeword engine to the one or more particular local wakewords during playback of the second portion of the audio content by the playback device; and playing back the second portion of the audio content via one or more speakers.

[0004f] Yet another aspect of the present disclosure is directed to a method to be performed by a playback device, the method comprising: receiving audio content for playback by the playback device; providing a sound data stream representing the received audio content to (i) a voice assistant service (VAS) wake-word engine and (ii) a local wakeword engine, wherein die VAS wake-word engine is operable to (a) generate a VAS wake word response when the VAS wake-word engine detects a VAS wake word in a microphone sound data stream representing sound detected by one or more microphones of the playback device and (b) stream sound data representing the sound detected by the one or more microphones to one or more servers of the VAS when the VAS wake word response is generated, and wherein the local wakeword engine is operable to (a) generate a local wakeword response when the local wakeword engine detects one or more local wakewords in the microphone sound data stream representing sound detected by the one or more microphones and (b) determine an

3a

Date Reçue/Date Received 2022-07-29 intent of a voice input comprising toe one or more local wakewords when the local wakeword response is generated; playing back a first portion of the audio content via one or more speakers; detecting, via the local wakeword engine, that a second portion of the received audio content includes sound data matching one or more particular local wakewords; before the second portion of the received audio content that includes the sound data matching the one or more particular local wakewords is played back, disabling the local wakeword response of the local wakeword engine to toe one or more particular local wakewords during playback of the second portion of the audio content by the playback device; and playing back the second portion of the audio content via one or more speakers.

[0004g] Yet another aspect of the present disclosure is directed to a tangible, non-transitory computerreadable medium having instructions stored thereon that, when executed by one or more processors of a playback device, cause the playback device to perform functions comprising: receiving audio content for playback by Ae playback device; providing a sound data stream representing Ae received audio content to (i) a voice assistant service (VAS) wake-word engine and (ii) a local wakeword engine, wherein toe VAS wake-word engine is operable to (a) generate a VAS wake word response when toe VAS wake-word engine detects a VAS wake word in a microphone sound data stream representing sound detected by one or more microphones of toe playback device and (b) stream sound data representing Ae sound detected by Ae one or more microphones to one or more servers of Ae VAS when Ae VAS wake word response is generated, and wherein Ae local wakeword engine is operable to (a) generate a local wakeword response when Ae local wakeword engine detects one or more local wakewords in Ae microphone sound data stream representing sound detected by Ae one or more microphones and (b) determine an intent of a voice input comprising Ae one or more local wakewords when Ae local wakeword response is generated; playing back a first portion of Ae audio content via one or more speakers; detecting, via Ae local wakeword engine, Aat a second portion of Ae received audio content includes sound data matching one or more particular local wakewords; before Ae second portion of Ae received audio content Aat includes Ae sound data matching Ae one or more particular local wakewords is played back, disabling Ae local wakeword response of Ae local wakeword engine to Ae one or more particular local wakewords during playback of Ae second portion of Ae audio content by the playback device; and playing back Ae second portion of Ae audio content via one or more speakers.

Date Reçue/Date Received 2022-07-29

BRIEF DESCRIPTION OF THE DRAWINGS

[0005] Features, aspects, and advantages of the presently disclosed technology may be better understood with regard to the following description and accompanying drawings where:

[0006] Figure 1 shows an example media playback system configuration in which certain embodiments may be practiced;

[0007] Figure 2 shows a functional block diagram of an example playback device;

[0008] Figure 3 shows a functional block diagram of an example control device;

[0009] Figure 4 shows an example controller interface;

[0010] Figure 5 shows an example processing system;

[0011] Figure 6 shows an example plurality of network devices according to aspects described herein;

[0012] Figure 7 shows a function block diagram of an example network microphone device according to aspects described herein;

[0013] Figure 8 shows an example flow diagram to disable a wake response of one or more MDs;

[0014] Figure 9 show example messages to cause a NMD to disregard a wake word;

[0015] Figures 10A, 10B, 1 OC, 10D illustrate example instructions to cause a NMD to disregard a wake word;

[0016] Figure 11 shows an example flow diagram to disable a wake response of one or more NMDs;

[0017] Figure 12 shows an example flow diagram to disable a wake response of one or more NMDs; and

[0018] Figure 13 shows an example flow diagram to suppress a wake response.

[0019] The drawings areforthe purpose of illustrating example embodiments, but it is understood that the inventions are not limited to the arrangements and instrumentality shown in the drawings.

Date reçue / Date received 2021-11-29

DETAILED DESCRIPTION

I. Overview

[0020] Networked microphone devices (NMDs) may be used to control a household using voice control. A NMD may be or may be part of, for example, a SONOS® playback device, server, or system capable of receiving voice input via a microphone. In some examples, the playback device is a SONOS® playback device. Additionally, a NMD may be or may be part of another device, server, or system (e.g., an AMAZON® ECHO®, APPLE® IPHONE®, among other examples) capable of receiving voice inputs via a microphone. U.S. App. No. 15/438,749 filed on February 21, 2017 and titled, Voice Control of a Media Playback System, provides examples of voice-enabled household architectures. Voice control can be beneficial for various devices with a smart home, such as playback devices, wireless illumination devices, thermostats, door locks, home automation, as well as other examples.

[0021] In some implementations, voice inputs detected by a NMD are sent to a voice service for processing. A NMD together with a playback device may operate as a microphone/speaker interface to the voice service. Voice inputs are detected by a microphone of the NMD and then transmitted to a particular voice service for processing. The voice service may then return a command or other result of the voice input.

[0022] Utterance of a wake word may invoke a voice service. For instance, in querying the AMAZON® voice service, a user might speak the wake word Alexa followed by a voice input. Other examples include Ok, Google for querying the GOOGLE® voice service and Hey, Siri for querying the APPLE® voice service. Other examples of wake words and voice services exist. Upon detecting a wake word, a NMD may respond by listening, via a microphone, for a voice command following the wake word. This response is referred to herein as the wake response of a NMD.

[0023] In some circumstances, playback of audio content that includes a wake word may falsely trigger the wake-response of a NMD. Wake-words for many voice services are pre-existing words chosen from the vocabulary of an existing language. For instance, several popular voice services use given names as wake words (e.g., Alexa and Siri). Accordingly, in some circumstances, recorded audio content such as a talk show, a film, a television show, a podcast, an Internet streaming video, among others, may include a wake word or similar. Playback of such audio content in range of a NMD

Date reçue / Date received 2021-11-29 may falsely trigger the NMD, which may be undesirable for many reasons including that it may interfere with enjoyment of the audio content

[0024] For example, a television may play back a commercial for a given voice service. During the commercial, an actor or actress might speak the wake word for the voice service, perhaps to demonstrate how the voice service is invoked. An NMD in the same room as the television might detect the audio output from the television, and invoke the voice service when the NMD detects the wake word in die commercial. This may be undesirable. Moreover, since die commercial may play on many televisions simultaneously, the commercial may trigger many NMDs at the same time, which may cause an undesirable surge in requests to the voice service.

[0025] To avoid their commercials causing false triggering, an operator of a voice service may mark the portion(s) of their commercial that includes a wake word and program their NMDs to ignore these marked portion(s). For instance, die operator may mix in a tone or other audio marker into commercials for the voice service and program their NMDs to ignore wake words that are detected in conjunction with this audio marker. This implementation may be useful in limited instances, such as commercials for die voice service, where the operator of the voice service can embed this marker into the audio content. However, this implementation is not useful with respect to the vast majority of other audio content over which the operator of the voice service has no control.

[0026] Example techniques described herein may involve processing audio content to be played back by a playback device before the audio content is audibly played back by the playback device, determining whether the audio content includes one or more wake words, and notifying one or more NMDs to disregard the wake word(s) when they are played back by the playback device. In this manner, the techniques may help prevent false triggering of NMDs. Notably, such techniques may be applicable to any recorded audio content to be played back by a playback device.

[0027] For instance, a playback device may receive audio content for playback. Before playing the audio content, the playback device stores the audio content in memory (e.g., in a buffer), and runs a wake word detection algorithm on the audio content. If any wake words are detected in the audio content, the playback device (which may be a NMD itself) causes one or more NMDs to disregard these wake words when the playback device ultimately plays back the audio content. [0028] As another example, a NMD may receive audio content that has been designated for playback by a playback device. Before the audio content is played back by the playback device, the NMD may run a wake word detection algorithm on the audio content. If any wake words are detected in the audio

Date reçue / Date received 2021-11-29 content, the NMD may cause itself (and possibly other NMDs in the vicinity) to disregard these wake words wham they are ultimately played back by the playback device.

[0029] An NMD may disregard a wake word using any of a variety of techniques. In some instances, the NMD may be instructed to not detect the wake word as it is played back by the playback device, perhaps by instructing the NMD to stop listening for wake words, by disabling the microphone array of the NMD for a period of time, or by creating a listening NULL in the direction of the playback device, among other examples. Alternatively, the NMD may proceed to initially detect the wake word, but be instructed to suppress its programmed wake response to invoke a voice service in response to detecting the wake word, perhaps by disregarding wake words during certain periods of time or by disregarding all recorded audio during certain periods of time.

[0030] When processing the audio content prior to the playback device audibly playing back that audio content, a processing device (such as a playback device or NMD) can also determine what sections of the recorded audio content contain the wake words. These sections can be defined by a time period within the audio content such as a start and stop time for the wake word (e.g., a wake word in a podcast starts at 33 :52.543 and ends at 33 :54.013). When the audio content is played back, NMDs in the vicinity can be instructed to ignore wake words during these time periods.

[0031] As another example, the processing device may count the number of wake words in the audio content (or in a portion of the audio content). For instance, a playback device that is processing the audio content of a commercial might detect four instances of a wake word in that commercial. Then, the playback device may instruct NMDs in the vicinity of the playback device to ignore wake words until they have detected a number of wake words equal to the count (e.g., to ignore the next four wake words).

[0032] In other examples, the processing device may dynamically insert an audio tone or other marker in the recorded audio content to designate wake words detected in the audio content. Then, when the audio content is played back by the playback device, a NMD that detects the audio maiker in conjunction with the wake word can be instructed to ignore that instance of the wake word. Multiple NMDs in audible range of the playback device may each detect the wake word and ignore the wake word in response to detecting the associated audio marker.

[0033] Example techniques may involve disabling wake response of one or more NMDs. A first implementation may include receiving, via a network interface, data representing audio content for

Date reçue / Date received 2021-11-29 playback by the playback device, and before the audio content is played back by the playback device, detecting, in the audio content, one or more wake words for one or more voice services. The first implementation may also include causing one or more networked microphone devices to disable its respective wake response to the detected one or more wake words during playback of the audio content by the playback device, where, when enabled, the wake response of a given networked microphone device to a particular wake word causes the given networked microphone device to listen, via a microphone, for a voice command following die particular wake word. The first implementation may further include playing back the audio content via one or more speakers.

[0034] A second implementation may include receiving, via a network interface, data representing audio content for playback by a playback device. The second implementation may also include, before the audio content is played back by the playback device, detecting, in the audio content, one or more wake words for one or more voice services. The second implementation may further include disabling a wake response of the networked microphone device to the detected one or more wake words during playback of the audio content by the playback device, and while the playback device is playing back the audio content, detecting the played back audio content via the microphone.

[0035] A third implementation may include receiving, via an interface of the computing system, audio content for playback by one or more playback devices. The third implementation may also include before the audio content is played back by the playback device, detecting, in the audio content, one or more wake words for one or more voice services. The third implementation may further include causing one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device.

[0036] A fourth implementation may include receiving, via the network interface, an instruction to disable a wake response of the networked microphone device to one or more wake words. The fourth implementation may also include detecting, via the microphone, audio content being played back by one or more playback devices. The fourth implementation may further include determining that the detected audio content includes one or more wake words and, in response to the received instruction, disabling the wake response of the networked microphone device to the one or more wake words in the detected audio content.

[0037] Each of the these example implementations may be embodied as a method, a device configured to cany out the implementation, a system of devices configured to cany out the implementation, or a non-transitory computer-readable medium containing instructions that are 8

Date reçue / Date received 2021-11-29 executable by one or more processors to carry out the implementation, among other examples. It will be understood by one of ordinary skill in the art that this disclosure includes numerous other embodiments, including combinations of the example features described herein. Further, any example operation described as being performed by a given device to illustrate a technique may be performed by any suitable devices, including the devices described herein. Yet further, any device may cause another device to perform any of the operations described herein.

[0038] While some examples described herein may refer to functions performed by given actors such as users and/or other entities, it should be understood that this description is for purposes of explanation only.

IL Example Operating Environment

[0039] Figure 1 illustrates an example configuration of a media playback system 100 in which one or more embodiments disclosed herein may be practiced or implemented. The media playback system 100 as shown is associated with an example home environment having several rooms and spaces, such as for example, a master bedroom, an office, a dining room, and a living room. As shown in the example of Figure 1, the media playback system 100 includes playback devices 102,104,106, 108,110,112,114,116,118,120,112, and 124, control devices 126 and 128, and a wired or wireless network router 130. Also present in Figure 1 are MDs 132 and 134.

[0040] Further discussions relating to die different components of die example media playback system 100 and how the different components may interact to provide a user with a media experience may be found in die following sections. While discussions herein may generally refer to the example media playback system 100, technologies described herein are not limited to applications within, among other things, the home environment as shown in Figure 1. For instance, the technologies described herein may be useful in environments where multi-zone audio may be desired, such as, for example, a commercial setting like a restaurant, mall or airport, a vehicle like a sports utility vehicle (SUV), bus or car, a ship or boat, an airplane, and so on.

a. Example Playback Devices

[0041] Figure 2 shows a functional block diagram of an example playback device 200 that may be configured to be one or more of the playback devices 102-124 of the media playback system 100 of Figure 1. The playback device 200 may include a processor 202, software components 204, memory 206, audio processing components 208, audio amplifier(s) 210, speakers) 212, and a network

Date reçue / Date received 2021-11-29 interface 214 including wireless interface(s) 216 and wired interface(s) 218. In one case, the playback device 200 may not include the speaker(s) 212, but rather a speaker interface for connecting the playback device 200 to external speakers. In another case, the playback device 200 may include neither the speaker(s) 212 nor the audio amplifier(s) 210, but rather an audio interface for connecting the playback device 200 to an external audio amplifier or audio-visual receiver.

[0042] In one example, the processor 202 may be a clock-driven computing component configured to process input data according to instructions stored in the memory 206. The memory 206 may be a tangible computer-readable medium configured to store instructions executable by the processor 202. For instance, the memory 206 may be data storage that can be loaded with one or more of the software components 204 executable by the processor 202 to achieve certain functions. In one example, the functions may involve the playback device 200 retrieving audio data from an audio source or another playback device. In another example, the functions may involve the playback device 200 sending audio data to another device or playback device on a network. In yet another example, the functions may involve pairing of the playback device 200 with one or more playback devices to create a multi-channel audio environment.

[0043] Certain functions may involve the playback device 200 synchronizing playback of audio content with one or more other playback devices. During synchronous playback, a listener will preferably not be able to perceive time-delay differences between playback of the audio content by the playback device 200 and the one or more other playback devices. U.S. Patent No. 8,234,395 entitled, System and method for synchronizing operations among a plurality of independently clocked digital data processing devices, provides in more detail some examples for audio playback synchronization among playback devices.

[0044] The memoiy 206 may further be configured to store data associated with the playback device 200, such as one or more zones and/or zone groups the playback device 200 is a part of, audio sources accessible by the playback device 200, or a playback queue that the playback device 200 (or some other playback device) may be associated with. The data may be stored as one or more state variables that are periodically updated and used to describe the state of the playback device 200. The memory 206 may also include toe data associated with toe state of toe other devices of toe media system, and shared from time to time among toe devices so that one or more of the devices have the most recent data associated with toe system. Other embodiments are also possible.

Date reçue / Date received 2021-11-29

[0045] The audio processing components 208 may include one or more digital-to-analog converters (DAC), an audio preprocessing component, an audio enhancement component or a digital signal processor (DSP), and so on. In one embodiment, one or more of the audio processing components 208 may be a subcomponent of the processor 202. In one example, audio content may be processed and/or intentionally altered by the audio processing components 208 to produce audio signals. The produced audio signals may then be provided to the audio amplifiers) 210 for amplification and playback through speakers) 212. Particularly, the audio amplifiers) 210 may include devices configured to amplify audio signals to a level for driving one or more of the speakers 212. The speakers) 212 may include an individual transducer (e.g., a driver) or a complete speaker system involving an enclosure with one or more drivers. A particular driver of the speakers) 212 may include, for example, a subwoofer (e.g., for low frequencies), a mid-range driver (e.g., for middle frequencies), and/or a tweeter (e.g., for high frequencies). In some cases, each transducer in the one or more speakers 212 may be driven by an individual corresponding audio amplifier of toe audio amplifier(s) 210. In addition to producing analog signals for playback by the playback device 200, toe audio processing components 208 may be configured to process audio content to be sent to one or more other playback devices for playback.

[0046] Audio content to be processed and/or played back by the playback device 200 may be received from an external source, such as via an audio line-in input connection (e.g., an auto-detecting 3.5mm audio line-in connection) or the network interface 214.

[0047] The network interface 214 may be configured to facilitate a data flow between the playback device 200 and one or more other devices on a data network. As such, the playback device 200 may be configured to receive audio content over the data network from one or more other playback devices in communication with the playback device 200, network devices within a local area network, or audio content sources over a wide area network such as the Internet. In one example, the audio content and other signals transmitted and received by the playback device 200 may be transmitted in the form of digital packet data containing an Internet Protocol (IP)-based source address and IP -based destination addresses. In such a case, the network interface 214 may be configured to parse the digital packet data such that the data destined for toe playback device 200 is properly received and processed by Ihe playback device 200.

[0048] As shown, the network interface 214 may include wireless interface(s) 216 and wired interface(s) 218. The wireless interface^) 216 may provide network interface functions for the

Date reçue / Date received 2021-11-29 playback device 200 to wirelessly communicate with other devices (e.g., other playback device(s), speaker(s), receiver(s), network device(s), control device(s) within a data network the playback device 200 is associated with) in accordance with a communication protocol (e.g., any wireless standard including IEEE 802.1 la, 802.1 lb, 802.11g, 802.1 1η, 802.1 lac, 802.15,4G mobile communication standard, and so on). The wired interface(s) 218 may provide network interface functions for the playback device 200 to communicate over a wired connection with other devices in accordance with a communication protocol (e.g., IEEE 802.3). While the network interface 214 shown in Figure 2 includes both wireless interface(s) 216 and wired interface(s) 218, the network interface 214 may in some embodiments include only wireless interface(s) or only wired interface(s).

[0049] In one example, the playback device 200 and one other playback device may be paired to play two separate audio components of audio content. For instance, playback device 200 may be configured to play a left channel audio component, while the other playback device may be configured to play a right channel audio component, thereby producing or enhancing a stereo effect of the audio content. The paired playback devices (also referred to as bonded playback devices) may further play audio content in synchrony with other playback devices.

[0050] In another example, the playback device 200 may be sonically consolidated with one or more other playback devices to form a single, consolidated playback device. A consolidated playback device may be configured to process and reproduce sound differently than an unconsolidated playback device or playback devices that are paired, because a consolidated playback device may have additional speaker drivers through which audio content may be rendered. For instance, if the playback device 200 is a playback device designed to render low frequency range audio content (i.e. a subwoofer), the playback device 200 may be consolidated with a playback device designed to render full frequency range audio content In such a case, the full frequency range playback device, when consolidated with the low frequency playback device 200, may be configured to render only the mid and high frequency components of audio content while the low frequency range playback device 200 renders the low frequency component of the audio content. The consolidated playback device may further be paired with a single playback device or yet another consolidated playback device.

[0051] By way of illustration, SONOS, Inc. presently offers (or has offered) for sale certain playback devices including a PLAY: 1, PLAY:3, PLAY:5, PLAYBAR, CONNECT: AMP, CONNECT, and SUB. Any other past, present, and/or future playback devices may additionally or alternatively be used to implement the playback devices of example embodiments disclosed herein.

Date reçue / Date received 2021-11-29

Additionally, it is understood Aat a playback device is not limited to Ae example illustrated in Figure 2 or to Ae SONOS product offerings. For example, a playback device may include a wired or wireless headphone. In anoAer example, a playback device may include or interact wiA a docking station for personal mobile media playback devices. In yet anoAer example, a playback device may be integral to anoAer device or component such as a television, a lighting fixture, or some oAer device for indoor or outdoor use.

b. Example Playback Zone Configurations

[0052] Referring back to Ae media playback system 100 of Figure 1, Ae environment may have one or more playback zones, each wiA one or more playback devices. The media playback system 100 may be established wiA one or more playback zones, after which one or more zones may be added, or removed to arrive at Ae example configuration shown in Figure 1. Each zone may be given a name according to a Afferent room or space such as an office, baAroom, master bedroom, bedroom, kitchen, dining room, living room, and/or balcony. A one case, a single playback zone may include multiple rooms or spaces. A anoAer case, a single room or space may include multiple playback zones.

[0053] As shown in Figure 1, Ae balcony, dining room, kitchen, baAroom, office, and bedroom zones each have one playback device, while Ae living room and master bedroom zones each have multiple playback devices. A Ae living room zone, playback devices 104,106,108, and 110 may be configured to play audio content in syncAony as individual playback devices, as one or more bonded playback devices, as one or more consolidated playback devices, or any combination Aereof. Similarly, in Ae case of Ae master bedroom, playback devices 122 and 124 may be configured to play audio content in synchrony as individual playback devices, as a bonded playback device, or as a consolidated playback device.

[0054] A one example, one or more playback zones in Ae environment of Figure 1 may each be playing Afferent audio content. For instance, Ae user may be grilling in Ae balcony zone and listening to hip hop music being played by Ae playback device 102 while anoAer user may be preparing food in Ae kitchen zone and listening to classical music being played by Ae playback device 114. A anoAer example, a playback zone may play Ae same auAo content in synchrony wiA anoAer playback zone. For instance, Ae user may be in Ae office zone where Ae playback device 118 is playing Ae same rock music Aat is being playing by playback device 102 in Ae balcony zone. A such a case, playback devices 102 and 118 may be playing Ae rock music in synchrony such Aat Ae user 13

Date reçue / Date received 2021-11-29 may seamlessly (or at least substantially seamlessly) enjoy the audio content that is being played outloud while moving between different playback zones. Synchronization among playback zones may be achieved in a manner similar to that of synchronization among playback devices, as described in previously referenced U.S. Patent No. 8,234,395.

[0055] As suggested above, Ae zone configurations of Ae media playback system 100 may be dynamically modified, and in some embodiments, foe media playback system 100 supports numerous configurations. For instance, if a user physically moves one or more playback devices to or from a zone, foe media playback system 100 may be reconfigured to accommodate foe change(s). For instance, if foe user physically moves the playback device 102 from foe balcony zone to the office zone, foe office zone may now include both foe playback device 118 and foe playback device 102. The playback device 102 may be paired or grouped with foe office zone and/or renamed if so desired via a control device such as foe control devices 126 and 128. On foe other hand, if foe one or more playback devices are moved to a particular area in foe home environment that is not already a playback zone, a new playback zone may be created for foe particular area.

[0056] Further, different playback zones of foe media playback system 100 may be dynamically combined into zone groups or split up into individual playback zones. For instance, foe dining room zone and foe kitchen zone 1 14 may be combined into a zone group for a dinner party such that playback devices 1 12 and 1 14 may render audio content in synchrony. On the oAer hand, the living room zone may be split into a television zone including playback device 104, and a listening zone including playback devices 106,108, and 1 10, if the user wishes to listen to music in the living room space while another user wishes to watch television.

c. Example Control Devices

[0057] Figure 3 shows a functional block diagram of an example control device 300 that may be configured to be one or both of the control devices 126 and 128 of foe media playback system 100. Control device 300 may also be referred to as a controller 300. As shown, foe control device 300 may include a processor 302, memory 304, a network interface 306, and a user interface 308. In one example, foe control device 300 may be a dedicated controller for foe media playback system 100. In another example, foe control device 300 may be a network device on which media playback system controller application software may be installed, such as for example, an iPhone™ iPad™ or any other smart phone, tablet or network device (e.g., a networked computer such as a PC or Mac™).

Date reçue / Date received 2021-11-29

[0058] The processor 302 may be configured to perform functions relevant to facilitating user access, control, and configuration of the media playback system 100. The memory 304 may be configured to store instructions executable by the processor 302 to perform those functions. The memory 304 may also be configured to store the media playback system controller application software and other data associated with the media playback system 100 and the user.

[0059] In one example, the network interface 306 may be based on an industry standard (e.g., infrared, radio, wired standards including IEEE 802.3, wireless standards including IEEE 802.1 la, 802.1 lb, 802.11g, 802.1 1η, 802.1 lac, 802.15,4G mobile communication standard, and so on). The network interface 306 may provide a means for the control device 300 to communicate with other devices in die media playback system 100. In one example, data and information (e.g., such as a state variable) may be communicated between control device 300 and other devices via the network interface 306. For instance, playback zone and zone group configurations in the media playback system 100 may be received by the control device 300 from a playback device or another network device, or transmitted by the control device 300 to another playback device or network device via toe network interface 306. In some cases, the other network device may be another control device.

[0060] Playback device control commands such as volume control and audio playback control may also be communicated from toe control device 300 to a playback device via the network interface 306. As suggested above, changes to configurations of the media playback system 100 may also be performed by a user using toe control device 300. The configuration changes may include adding/removing one or more playback devices to/from a zone, adding/removing one or more zones to/from a zone group, forming a bonded or consolidated player, separating one or more playback devices from a bonded or consolidated player, among others. Accordingly, toe control device 300 may sometimes be referred to as a controller, whether the control device 300 is a dedicated controller or a network device cm which media playback system controller application software is installed.

[0061] The user interface 308 of the control device 300 may be configured to facilitate user access and control of the media playback system 100, by providing a controller interface such as the controller interface 400 shown in Figure 4. The controller interface 400 includes a playback control region 410, a playback zone region 420, a playback status region 430, a playback queue region 440, and an audio content sources region 450. The user interface 400 as shown is just one example of a user interface that may be provided on a network device such as the control device 300 of Figure 3 (and/or toe control devices 126 and 128 of Figure 1) and accessed by users to control a media playback

Date reçue / Date received 2021-11-29 system such as the media playback system 100. Other user interfaces of varying formats, styles, and interactive sequences may alternatively be implemented on one or more network devices to provide comparable control access to a media playback system.

[0062] The playback control regi on 410 may include selectable (e.g., by way of touch or by using a cursor) icons to cause playback devices in a selected playback zone or zone group to play or pause, fast forward, rewind, skip to next, skip to previous, enter/exit shuffle mode, enter/exit repeat mode, enter/exit cross fade mode. The playback control region 410 may also include selectable icons to modify equalization settings, and playback volume, among other possibilities. [0063] The playback zone region 420 may include representations of playback zones within the media playback system 100. In some embodiments, the graphical representations of playback zones may be selectable to bring up additional selectable icons to manage or configure the playback zones in the media playback system, such as a creation of bonded zones, creation of zone groups, separation of zone groups, and renaming of zone groups, among other possibilities.

[0064] For example, as shown, a group icon may be provided within each of the graphical representations of playback zones. The group icon provided within a graphical representation of a particular zone may be selectable to bring up options to select one or more other zones in the media playback system to be grouped with the particular zone. Once grouped, playback devices in the zones that have been grouped with the particular zone will be configured to play audio content in synchrony with the playback device(s) in the particular zone. Analogously, a group icon may be provided within a graphical representation of a zone group. In this case, the group icon may be selectable to bring up options to deselect one or more zones in the zone group to be removed from the zone group. Other interactions and implementations for grouping and ungrouping zones via a user interface such as the user interface 400 are also possible. The representations of playback zones in the playback zone region 420 may be dynamically updated as playback zone or zone group configurations are modified.

[0065] The playback status region 430 may include graphical representations of audio content that is presently being played, previously played, or scheduled to play next in the selected playback zone or zone group. The selected playback zone or zone group may be visually distinguished on the user interface, such as within the playback zone region 420 and/or the playback status region 430. The graphical representations may include track title, artist name, album name, album year, track length, and other relevant information that may be useful for the user to know when controlling the media playback system via the user interface 400.

Date reçue / Date received 2021-11-29

[0066] The playback queue region 440 may include graphical representations of audio content in a playback queue associated with the selected playback zone or zone group. In some embodiments, each playback zone or zone group may be associated with a playback queue containing information corresponding to zero or more audio items for playback by the playback zone or zone group. For instance, each audio item in the playback queue may comprise a uniform resource identifier (URI), a uniform resource locator (URL) or some other identifier that may be used by a playback device in the playback zone or zone group to find and/or retrieve the audio item from a local audio content source or a networked audio content source, possibly for playback by the playback device.

[0067] In one example, a playlist may be added to a playback queue, in which case information corresponding to each audio item in the playlist may be added to the playback queue. In another example, audio items in a playback queue may be saved as a playlist. In a further example, a playback queue may be empty, or populated but not in use when ihe playback zone or zone group is playing continuously streaming audio content, such as Internet radio that may continue to play until otherwise stopped, rather than discrete audio items that have playback durations. In an alternative embodiment, a playback queue can include Internet radio and/or other streaming audio content items and be in use when the playback zone or zone group is playing those items. Other examples are also possible.

[0068] When playback zones or zone groups are grouped or ungrouped, playback queues associated with the affected playback zones or zone groups may be cleared or re-associated. For example, if a first playback zone including a first playback queue is grouped with a second playback zone including a second playback queue, the established zone group may have an associated playback queue that is initially empty, that contains audio items from the first playback queue (such as if the second playback zone was added to the first playback zone), that contains audio items from the second playback queue (such as if the first playback zone was added to the second playback zone), or a combination of audio items from both the first and second playback queues. Subsequently, if the established zone group is ungrouped, the resulting first playback zone may be re-associated with the previous first playback queue, or be associated with a new playback queue that is empty or contains audio items from the playback queue associated with the established zone group before the established zone group was ungrouped. Similarly, the resulting second playback zone may be re-associated with the previous second playback queue, or be associated with a new playback queue that is empty, or contains audio items from toe playback queue associated with toe established zone group before the established zone group was ungrouped. Other examples are also possible.

Date reçue / Date received 2021-11-29

[0069] Referring back to the user interface 400 of Figure 4, the graphical representations of audio content in the playback queue region 440 may include track titles, artist names, track lengths, and other relevant information associated with the audio content in the playback queue. In one example, graphical representations of audio content may be selectable to bring up additional selectable icons to manage and/or manipulate the playback queue and/or audio content represented in tire playback queue. For instance, a represented audio content may be removed from the playback queue, moved to a different position within the playback queue, or selected to be played immediately, or after any currently playing audio content, among other possibilities. Λ playback queue associated with a playback zone or zone group may be stored in a memoiy on one or more playback devices in the playback zone or zone group, on a playback device that is not in the playback zone or zone group, and/or some other designated device. Playback of such a playback queue may involve one or more playback devices playing back media items of the queue, perhaps in sequential or random order.

[0070] The audio content sources region 450 may include graphical representations of selectable audio content sources from which audio content may be retrieved and played by the selected playback zone or zone group. Discussions pertaining to audio content sources may be found in the following section,

d. Example Audio Content Sources

[0071] As indicated previously, one or more playback devices in a zone or zone group may be configured to retrieve for playback audio content (e.g., according to a corresponding URI or URL for the audio content) from a variety of available audio content sources. In one example, audio content may be retrieved by a playback device directly from a corresponding audio content source (e.g., a line-in connection). In another example, audio content may be provided to a playback device over a network via one or more other playback devices or netwoik devices.

[0072] Example audio content sources may include a memory of one or more playback devices in a media playback system such as the media playback system 100 of Figure 1, local music libraries on one or more network devices (such as a control device, a network-enabled personal computer, or a networked-attached storage (NAS), for example), streaming audio services providing audio content via the Internet (e.g., the cloud), or audio sources connected to the media playback system via a linein input connection on a playback device or network devise, among other possibilities.

Date reçue / Date received 2021-11-29

[0073] In some embodiments, audio content sources may be regularly added or removed from a media playback system such as the media playback system 100 of Figure 1. In one example, an indexing of audio items may be performed whenever one or more audio content sources are added, removed or updated. Indexing of audio items may involve scanning for identifiable audio items in all folders/directory shared over a network accessible by playback devices in the media playback system, and generating or updating an audio content database containing metadata (e.g., title, artist, album, track length, among others) and other associated information, such as a URI or URL for each identifiable audio item found. Other examples for managing and maintaining audio content sources may also be possible,

e. Example Processing System

[0074] Figure 5 shows a functional block diagram of an example processing system 500 that includes an audio input/output component 502, a wake word detection component 504, and a notification component 506. In operation, processing system 500 detects wake words within recorded audio content and provides notifications to NMDs to ignore or otherwise suppress their programmed wake response to detecting a wake word. Within various embodiments, processing system 500 may be implemented in a playback device, a NMD, or a separate processing device, such as a cloud server, among other examples. In some embodiments, various components of the processing system (and/or functionality thereof) are distributed among multiple devices.

[0075] In operation, audio input/output component 502 receives, via an input interface, recorded audio content designated for playback by a playback device. For instance, a control device (such as control device 126 or 128 of Figure 1) may instruct a playback device (e.g., any playback device of Figure 1 ) to play back certain audio content, perhaps by causing that content to be placed in a playback queue of the playback device to cause the playback device to retrieve the audio content, by directing an audio content stream to the playback device, or by directing audio content to die playback device via an analog or digital line-in interface, among other examples. The audio/input component 502 of the processing system 500 receives this recorded audio content before the audio content is played back by the playback device.

[0076] As noted above, in some examples, processing system 500 is implemented within a playback device. In such embodiments, the playback device 500 already has access to the audio content necessarily for playback. For instance, the playback device may receive the audio content from a network source (e.g., a streaming media service or a mobile device) via a network interface 19

Date reçue / Date received 2021-11-29 over one or more types of networks, such as wide area networks (WAN), local area networks (LAN), and personal area networks (PAN), among other possibilities. Alternatively, the playback device may receive the audio content via an analog (e.g., RCA) or digital (e.g., TosLink® or HDMI®) line-in interface.

[0077] In other examples, processing system 500 is implemented within a NMD or other processing device that is separate from the playback device. In such embodiments, processing system 500 may receive the audio content via a network interface from the playback device or from the source of the audio content, among other examples. In another example, a line-in interface may provide the audio content directly to the NMD or a playback device may receive the audio content via a line-in interface and relay the content to die processing system 500 over one or more networks.

[0078] For instance, processing system 500 may have access to the playback queue of the playback device. As noted above, each audio item in the playback queue may comprise a uniform resource identifier (URI), a uniform resource locator (URL) or some other identifier that may be used by a playback device in the playback zone or zone group to find and/or retrieve the audio item from a local audio content source or a networked audio content source, possibly for playback by the playback device. The processing system 500 may similarly use such an identifier to retrieve audio content from a local audio content source or a networked audio content source, prior to playback by the playback device.

[0079] In some implementations, the playback queue is stored in data storage of the playback device. In further implementations, the playback queue is stored on a cloud server. The playback queue stored on the cloud server (i.e., a cloud queue) may be an instance or representation of a playback queue stored on the playback device. The cloud queue may include a playback pointer or other status information representing the current state of playback on the playback device.

[0080] In some instances, processing system 500 may convert the received audio content into a format suitable for wake word detection. For instance, if the audio content is provided to the audio/input component 502 via an analog line-in interface, the processing system 500 may digitize the analog audio (e.g., using a software or hardware-based analog-to-digital converter). As another example, if the received audio content is received in a digital form that is unsuitable for analysis, the processing system 500 may transcode the recording into a suitable format.

Date reçue / Date received 2021-11-29

[0081] Wake-word detection component 504 analyzes the received audio content to determine if any wake words are present in the recording. The wake word detection component 504 may analyze the received audio content using a wake word detection algorithm. Example wake word detection algorithms accept an audio recording as input and provide an indication of whether a wake word is present in the recording as output.

[0082] In some implementations, the wake word detection component 504 may use the same algorithm on the recording as utilized by NMDs for detecting wake words in audio recorded via a microphone. During typical operation, an example NMD constantly records audio and provides the recorded audio stream into a wake-word detection algorithm, in order to determine if die recorded audio includes a wake word. Here, instead of providing audio that was recorded by die microphone of an NMD to the wake word detection algorithm, the wake word detection component 504 provides the pre-recorded audio content designated for playback.

[0083] During analysis, the wake word detection component 504 additionally determines where each wake word occurs in the received audio content. For instance, the wake word detection component 504 may divide the received audio content into segments of known length. Then, the wake word detection component 504 can determine where in the recording that the wake-word occurs by identifying the segment that the wake word was detected. For example, if each segment is 5 seconds long and the wake word was detected in the fourth segment, the wake word must be located between 15 and 20 seconds into the recording. The wake word detection component 504 may record the portions of the audio content containing a wake word, perhaps using one or more timestamps (e.g., a time stamp indicating a start time for the wake-word, and perhaps another timestamp indicating a stop time for that wake word). Such time stamps may define respective time offsets from the start of an audio recording or from another particular position in the audio recording. In some instances, the wake word detection component 504 may separate the audio recording into overlapping segments, to avoid breaking apart a wake word into unrecognizable portions. Other techniques for determining the location of a wake word within the audio recording can be utilized as well.

[0084] Within examples, processing system 500 may buffer the received audio content in memory. For instance, processing system 500 may store the received audio content in a first-in-firstout buffer (e.g., a circular buffer). In such implementations, portions of the received audio are stored in the buffer when they are received, and are removed as they are processed to determine if the received audio content contains wake words.

Date reçue / Date received 2021-11-29

[0085] In some instances, the wake word detection component 504 runs multiple wake word detections algorithms on the received audio content simultaneously (or substantially simultaneously). As noted above, different voice services (e.g. AMAZON’S ALEXA®, APPLE'S SIRI®, or MICROSOFT'S CORTANA®) each use a different wake word for invoking their respective voice service. To support multiple services, the wake word detection component 504 may run the received audio content through the wake word detection algorithm for each supported voice service in parallel.

[0086] If one or more wake words are detected in the audio content, notification component 506 notifies one or more NMDs (e.g., NMDs 132 and/or 134 of Figure 1). This notification causes a NMD to disregard the detected wake words when they are played back in the course of a playback device playing back the audio content that includes the wake words. For instance, the notification component 506 may send instructions over a network interface to one or more NMDs to disregard certain wake words or a certain number of wake words.

[0087] In some instances, the notification component 506 may prevent a NMD from detecting the wake word as it is played back by the playback device. For instance, the notification component 506 may instruct the NMD to stop listening for wake words (e.g., to stop processing recorded audio) for a period of time. Alternatively, the notification component 506 may instruct the NMD to disable its microphone array temporarily (e.g., during the period of time corresponding to when the wake words are expected to be played by the playback device). As yet another example, the notification component 506 may instruct the NMD to create a listening NULL in the direction of the playback device using its microphone array, so that the NMD does not detect the wake word. Other examples are possible as well.

[0088] Alternatively, the NMD may detect the wake word, but the notification component 506 instructs the NMD to suppress its programmed wake response to invoke a voice service in response to detecting the wake word. For instance, the notification component 506 may instruct the NMD to disregard wake words during certain periods of time or to disregard all audio during certain periods of time. Other examples are possible as well.

[0089] When processing the audio content prior to the playback device audibly playing back that audio content, a processing device (such as a playback device or NMD) can also determine what sections of the recorded audio content contain the wake words. These sections can be defined by a time period within the audio content such as a start and stop time for the wake word (e.g., a wake

Date reçue / Date received 2021-11-29 word in a podcast starts at 33:52.543 and ends at 33:54.013). When the audio content is played back,

NMDs in the vicinity can be instructed to ignore wake words during these time periods.

[0090] As another example, the processing system 500 may count the number of wake words in the audio content (or in a portion of the audio content). For instance, the processing system 500 might detect three wake words in an example audio content (e.g., a television show). As noted above, such instances may include any combination of wake words, including different wake words for different voice services. Then, the processing system 500 may instruct MDs in the vicinity to ignore wake words until they have detected a number of wake words equal to the count (e.g., to ignore the next three wake words).

[0091] In other examples, processing system 500 may dynamically insert an audio tone or other marker in the recorded audio content to designate wake words detected in the audio content. Then, when the audio content is played back by the playback device, a NMD that detects the audio marker in conjunction with the wake word can be instructed to ignore that instance of the wake word. If multiple NMDs are in audible range of the playback device, each NMD that detect a wake word may ignore it in response to detecting the associated audio marker. In some cases, the audio marker is composed of audio frequencies that are outside the range of human hearing (e.g., above 20 kHz), so that the inserted tone is not noticeable by human listeners.

[0092] In some implementations, processing system 500 operates as an intermediary between a source of audio content and the playback device. For instance, in implementations where foe processing system 500 notifies NMDs using an audio marker, the processing system modifies the audio content designated for playback by the playback device. In such implementations, the processing system 500 may receive foe audio content from an audio source (e.g., via a network or line-in interface), analyze foe audio content, and provide the modified audio content to foe playback device for playback, perhaps via a network interface.

[0093] Alternatively, as noted above, processing system 500 is implemented in the playback device itself. In such instances, after analyzing the audio content, the playback device may proceed to play back the audio content Further, as noted above, in some cases, the playback device may be configured to play back audio content in synchrony with one or more additional playback devices (e.g., in a zone group, stereo pair, or surround sound configuration). In such circumstances, foe playback device may provide foe (possibly modified) audio content to the one or more additional playback devices, perhaps via a network interface.

Date reçue / Date received 2021-11-29

[0094] In further examples, processing system 500 is implemented in a NMD. In such instances, processing system 500 may cause the NMD itself to ignore the wake words in audio content when it is played back. Further, the NMD may instruct other NMDs to ignore the wake word. For instance, NMD 132 may instruct NMD 134 to ignore the wake word. Further, if a NMD is implemented in a playback device (e.g., playback device 104), the NMD/playback device may instruct other NMD’s (which may themselves be implemented in playback devices) to ignore the wake words,

f. Example Plurality of Networked Devices

[0095] Figure 6 shows an example plurality of devices 600 that may be configured to provide an audio playback experience based on voice control. One having ordinary skill in die art will appreciate that the devices shown in Figure 6 are for illustrative purposes only, and variations including different and/or additional devices may be possible. As shown, the plurality of devices 600 includes computing devices 604,606, and 608; network microphone devices (NMDs) 612,614, and 616; playback devices (PBDs) 632,634,636, and 638; and a controller device (CR) 622.

[0096] Each of the plurality of devices 600 may be network-capable devices that can establish communication with one or more other devices in the plurality of devices according to one or more network protocols, such as NFC, Bluetooth, Ethernet, and IEEE 802.1 1, among other examples, over one or more types of networks, such as wide area networks (WAN), local area networks (LAN), and personal area networks (PAN), among other possibilities.

[0097] As shown, the computing devices 604,606, and 608 may be part of a cloud network 602. The cloud network 602 may include additional computing devices. In one example, the computing devices 604,606, and 608 may be different servers. In another example, two or more of the computing devices 604, 606, and 608 may be modules of a single server. Analogously, each of the computing device 604, 606, and 608 may include one or more modules or servers. For ease of illustration purposes herein, each of the computing devices 604, 606, and 608 may be configured to perform particular functions within the cloud network 602. For instance, computing device 608 may be a source of audio content for a streaming music service.

[0098] As shown, the computing device 604 may be configured to interface with NMDs 612, 614, and 616 via communication path 642. NMDs 612, 614, and 616 may be components of one or more Smart Home systems. In one case, NMDs 612, 614, and 616 may be physically distributed throughout a household, similar to the distribution of devices shown in Figure 1. In another case, two

Date reçue / Date received 2021-11-29 or more of Ae NMDs 612,614, and 616 may be physically positioned wiAin relative close proximity of one anoAer. Communication paA 642 may comprise one or more types of networks, such as a

WAN including Ae Internet, LAN, and/or PAN, among oAer possibilities.

[0099] In one example, one or more of Ae NMDs 612,614, and 616 may be devices configured primarily for audio detection. In anoAer example, one or more of Ae NMDs 612,614, and 616 may be components of devices having various primary utilities. For instance, as discussed above in connection to Figures 2 and 3, one or more of NMDs 612, 614, and 616 may be Ae microphone(s) 220 of playback device 200 or Ae microphone(s) 310 of network device 300. Further, in some cases, one or more of NMDs 612,614, and 616 may be Ae playback device 200 or network device 300. In an example, one or more of NMDs 612,614, and/or 616 may include multiple microphones arranged in a microphone array.

[0100] As shown, Ae computing device 606 may be configured to interface wiA CR 622 and PBDs 632,634,636, and 638 via communication paA 644. In one example, CR 622 may be a network device such as Ae network device 200 of Figure 2. Accordingly, CR 622 may be configured to provide Ae controller interface 400 of Figure 4. Similarly, PBDs 632, 634, 636, and 638 may be playback devices such as Ae playback device 300 of Figure 3. As such, PBDs 632,634,636, and 638 may be physically distributed Aroughout a household as shown in Figure 1. For illustration purposes, PBDs 636 and 638 may be part of a bonded zone 630, while PBDs 632 and 634 may be part of Aeir own respective zones. As described above, Ae PBDs 632,634,636, and 638 may be dynamically bonded, grouped, unbonded, and ungrouped. Communication paA 644 may comprise one or more types of networks, such as a WAN including Ae Internet, LAN, and/or PAN, among oAer possibilities.

[0101] In one example, as wiA NMDs 612, 614, and 616, CR 622 and PBDs 632,634,636, and 638 may also be components of one or more Smart Home systems. In one case, PBDs 632, 634, 636, and 638 may be distributed Aroughout Ae same household as Ae NMDs 612, 614, and 616. Further, as suggested above, one or more of PBDs 632, 634, 636, and 638 may be one or more of NMDs 612,614, and 616.

[0102] The NMDs 612,614, and 616 may be part of a local area network, and Ae communication paA 642 may include an access point Aat links Ae local area netwoik of Ae NMDs 612,614, and 616 to Ae computing device 604 over a WAN (communication paA not shown). Likewise, each of Ae NMDs 612,614, and 616 may communicate wiA each oAer via such an access point.

Date reçue / Date received 2021-11-29

[0103] Similarly, CR 622 and PBDs 632,634,636, and 638 may be part of a local area network and/or a local playback network as discussed in previous sections, and the communication path 644 may include an access point that links the local area network and/or local playback network of CR

622 and PBDs 632,634,636, and 638 to the computing device 606 over a WAN. As such, each of the

CR 622 and PBDs 632,634,636, and 638 may also communicate with each over such an access point.

[0104] In one example, communication paths 642 and 644 may comprise the same access point. In an example, each of the NMDs 612,614, and 616, CR 622, and PBDs 632,634,636, and 638 may access the cloud network 602 via the same access point for a household.

[0105] As shown in Figure 6, each of the NMDs 612,614, and 616, CR 622, and PBDs 632,634,

636, and 638 may also directly communicate with one or more of the other devices via communication means 646. Communication means 646 as described herein may involve one or more forms of communication between the devices, according to one or more network protocols, over one or more types of networks, and/or may involve communication via one or more other network devices. For instance, communication means 646 may include one or more of for example, Bluetooth™ (IEEE 802.15), NFC, Wireless direct, and/or Proprietary wireless, among other possibilities.

[0106] In one example, CR 622 may communicate with NMD 612 over Bluetooth™, and communicate with PBD 634 over another local area network. In another example, NMD 614 may communicate with CR 622 over another local area network, and communicate with PBD 636 over Bluetooth. In a further example, each of the PBDs 632, 634, 636, and 638 may communicate with each other according to a spanning tree protocol over a local playback network, while each communicating with CR 622 over a local area network, different from the local playback network. Other examples are also possible.

[0107] In some cases, communication means between the NMDs 612,614, and 616, CR 622, and

PBDs 632,634,636, and 638 may change depending on types of communication between the devices, network conditions, and/or latency demands. For instance, communication means 646 may be used when NMD 616 is first introduced to the household with the PBDs 632, 634, 636, and 638. In one case, the NMD 616 may transmit identification information corresponding to the NMD 616 to PBD 638 via NFC, and PBD 638 may in response, transmit local area netwoik information to NMD 616 via NFC (or some other form of communication). However, once NMD 616 has been configured within the household, communication means between NMD 616 and PBD 638 may change. For instance, NMD 616 may subsequently communicate with PBD 638 via communication path 642, the 26

Date reçue / Date received 2021-11-29 cloud network 602, and communication path 644. In another example, the NMDs and PBDs may never communicate via local communications means 646. In a further example, the NMDs and PBDs may communicate primarily via local communications means 646. Other examples are also possible.

[0108] In an illustrative example, NMDs 612, 614, and 616 may be configured to receive voice inputs to control PBDs 632, 634, 636, and 638. The available control commands may include any media playback system controls previously discussed, such as playback volume control, playback transport controls, music source selection, and grouping, among other possibilities. In one instance, NMD 612 may receive a voice input to control one or more of the PBDs 632, 634, 636, and 638. In response to receiving the voice input, NMD 612 may transmit via communication path 642, the voice input to computing device 604 for processing. In one example, die computing device 604 may convert the voice input to an equivalent text command, and parse the text command to identify a command. Computing device 604 may then subsequently transmit the text command to the computing device 606. In another example, the computing device 604 may convert the voice input to an equivalent text command, and dien subsequently transmit the text command to die computing device 606. The computing device 606 may then parse the text command to identify one or more playback commands.

[0109] For instance, if the text command is Play ’Track by 'Artist from 'Streaming Service in 'Zone, The computing device 606 may identify (i) a URL for Track 1 by Artist 1 available from Streaming Service 1, and (ii) at least one playback device in Zone 1. In this example, the URL for Track 1 by Artist 1 from Streaming Service 1 may be a URL pointing to computing device 608, and Zone 1 may be the bonded zone 630. As such, upon identifying the URL and one or both of PBDs 636 and 638, the computing device 606 may transmit via communication path 644 to one or both of PBDs 636 and 638, the identified URL for playback. One or both of PBDs 636 and 638 may responsively retrieve audio content from the computing device 608 according to the received URL, and begin playing Track 1 by Artist 1 from Streaming Service 1.

[0110] In yet another example, the computing device 604 may perform some processing to identify the relevant command or intent of the user and provide information regarding media content relevant to the voice input to the computing device 606. For example, the computing device 604 may perform the speech-to-text conversion of the voice input and analyze the voice input for a command or intent (e.g., play, pause, stop, volume up, volume down, skip, next, group, ungroup) along with other information about how to execute the command. The computing device 604 or the computing device 606 may determine what PBD commands correspond to the command or intent determined by

Date reçue / Date received 2021-11-29

Ae computing device 604. The command or intent determined from Ae voice input and/or oAer information related to executing Ae command may be transmitted from Ae computing device 604 to

Ae computing device 606. The processing on Ae computing device 604 may be performed by an application, a module, add-on software, an integration wiA Ae native networked microphone system software platform, and/or Ae native networked microphone system software platform.

[0111] One having ordinary skill in Ae art will appreciate Aat Ae above is just one illustrative example, and Aat oAer implementations are also possible. A one case, operations performed by one or more of Ae plurality of devices 600, as described above, may be performed by one or more oAer devices in Ae plurality of device 600. For instance, Ae conversion from voice input to Ae text command may be alternatively, partially, or wholly performed by anoAer device or devices, such as NMD 612, computing device 606, PBD 636, and/or PBD 638. Analogously, Ae identification of Ae URL may be alternatively, partially, or wholly performed by anoAer device or devices, such as NMD 612, computing device 604, PBD 636, and/or PBD 638.

f. Example Network Microphone Device

[0112] Figure 7 shows a function block diagram of an example network microphone device 700 Aat may be configured to be one or more of NMDs 712, 714, and 716 of Figure 7. As shown, Ae network microphone device 700 includes a processor 702, memory 704, a microphone array 706, a network interface 708, a user interface 710, software components 712, and speaker(s) 714. One having ordinary skill in Ae art will appreciate Aat oAer network microphone device configurations and arrangements are also possible. For instance, network microphone devices may alternatively exclude Ae speakers) 714 or have a single microphone instead of microphone array 706.

[0113] The processor 702 may include one or more processors and/or controllers, which may take Ae form of a general or special-puipose processor or controller. For instance, Ae processing unit 702 may include microprocessors, microcontrollers, application-specific integrated circuits, digital signal processors, and Ae like. The memory 704 may be date storage Aat can be loaded wiA one or more of Ae software components executable by Ae processor 702 to perform Aose functions. Accordingly, memory 704 may comprise one or more non-transitory computer-readable storage mediums, examples of which may include volatile storage mediums such as random access memory, registers, cache, etc. and non-volatile storage mediums such as readonly memory, a hard-disk drive, a solid-state drive, flash memory, and/or an optical-storage device, among oAer possibilities.

Date reçue / Date received 2021-11-29

[0114] The microphone array 706 may be a plurality of microphones arranged to detect sound in the environment of the network microphone device 700. Microphone array 706 may include any type of microphone now known or later developed such as a condenser microphone, electret condenser microphone, or a dynamic microphone, among other possibilities. In one example, the microphone array may be arranged to detect audio from one or more directions relative to the network microphone device. The microphone array 706 may be sensitive to a portion of a frequency range. In one example, a first subset of die microphone array 706 may be sensitive to a first frequency range, while a second subset of the microphone array may be sensitive to a second frequency range. The microphone array 706 may further be arranged to capture location information of an audio source (e.g., voice, audible sound) and/or to assist in filtering background noise. Notably, in some embodiments the microphone array may consist of only a single microphone, rather than a plurality of microphones.

[0115] The network interface 708 may be configured to facilitate wireless and/or wired communication between various network devices, such as, in reference to Figure 7, CR 722, PBDs 732-738, computing device 704-708 in cloud network 702, and other network microphone devices, among other possibilities. As such, network interface 708 may take any suitable form for carrying out these functions, examples of which may include an Ethernet interface, a serial bus interface (e.g., Fire Wire, USB 2.0, etc.), a chipset and antenna adapted to facilitate wireless communication, and/or any other interface that provides for wired and/or wireless communication. In one example, the network interface 708 may be based on an industry standard (e.g., infrared, radio, wired standards including IEEE 802.3, wireless standards including IEEE 802.1 la, 802.1 lb, 802.1 1g, 802.1 1η, 802.1 lac, 802.15,4G mobile communication standard, and so on).

[0116] The user interface 710 of the network microphone device 700 may be configured to facilitate user interactions with the network microphone device. In one example, the user interface 708 may include one or more of physical buttons, graphical interfaces provided on touch sensitive screen(s) and/or surface(s), among other possibilities, for a user to directly provide input to tire network microphone device 700. The user interface 710 may further include one or more of lights and the speakers) 714 to provide visual and/or audio feedback to a user. In one example, the network microphone device 700 may further be configured to playback audio content via the speakers) 714.

III. Example Techniques For A Playback Device To Disable A Wake-Response

Date reçue / Date received 2021-11-29

[0117] As discussed above, embodiments described herein may involve disabling a wake response. Figure 8 illustrates an example implementation 800 by which a playback device disables a wake response of one or more MDs.

a. Receive Data Representing Audio Content For Playback

[0118] At block 802, implementation 802 involves receiving data representing audio content for playback. For instance, a playback device may receive audio content for playback by the playback device. Example playback devices include any of playback devices 102,104, 106, 108,1 10,1 12,1 14,1 16,1 18,120, 1 12, and 124 shown in Figure 1, which may be implemented as represented by playback device 200 of Figure 2, for instance. In some implementations, the playback device may include a processing system (e.g., processing system 500) and receive the data representing the audio content using an audio input/output component (such as audio input/output component 502 of Figure 5).

[0119] Example audio content includes one or more audio tracks, a talk show, a film, a television show, a podcast, an Internet streaming video, among many possible other forms of audio content. The audio content may include audio content that is accompanied by video (e.g., an audio track of a video) or audio that is unaccompanied by video.

[0120] The playback device may receive the audio content via an input interface, which may be a wired or wireless network interface or an analog or digital line-in interface, among other examples. For instance, the playback device may receive the audio content from a network source via a network interface over one or more types of networks, such as wide area networks (WAN), local area networks (LAN), and personal area networks (PAN), among other possibilities.

[0121] The playback device may receive the data representing the audio content from a local or remote audio source. For instance, the playback device may receive the audio content from a local media server or other device on a local area network, from a medium (such as a CD, DVD, Blu-Ray, flash memory, or hard drive) that is read by the playback device or by another device in communication with the playback device (e.g., over a local area network via a network interface), or from data storage on the playback device itself. The playback device may receive the audio content as an audio content stream, perhaps from one or more cloud servers. For instance, the playback device may retrieve an audio content stream from a URL via a network interface. Alternatively, the playback device may receive the audio content from a line-in interface on the playback device or on another

Date reçue / Date received 2021-11-29 device in communication with the playback device (e.g., over a local area network via a network interface).

[0122] In some cases, the playback device may receive audio content in analog format, perhaps via an analog line-in interface. In such instances, the playback device digitizes the analog audio (e.g., using a software or hardware-based analog-to-digital converter) into a format suitable for processing. Alternatively, a device in communication with the playback device may receive audio content in analog format, digitize the audio content, and transmit data representing the audio content to the playback device.

[0123] As noted above, the received audio content is designed for playback by the playback device. For instance, a control device (such as control device 126 or 128 of Figure 1) may instruct the playback device to play back certain audio content, perhaps by causing that content to be placed in a playback queue of the playback device. Placing an audio track or other audio content into such a queue causes the playback device to retrieve the audio content, peihaps after playback is initiated via a control that is on the control device or on the playback device itself (e.g., a Play/Pause button). The playback device may retrieve the audio content from the local or remote audio source by directing an audio content stream to the playback device via a network interface or by directing audio content to the playback device via an analog or digital line-in interface, among other examples.

[0124] Within examples, the playback device may store at least a portion of the received audio content in memory. For instance, the playback device may buffer received audio content in a first-infirst-out buffer (e.g., a circular buffer). In such implementations, portions of the received audio are stored in the buffer when they are received, and are removed as they are processed which enables the playback device to determine if the received audio content contains wake words.

b. Detect. In The Audio Content. One Or More Wake Words

[0125] Referring back to Figure 8, at block 804, implementation 800 involves detecting, in the audio content, one or more wake-words before the audio content is played back by the playback device. For instance, the playback device may analyze the received data representing the audio content to determine if wake words for any voice services are represented in the audio content, such that when the audio content is played back, the wake words will be played audibly. As noted above, in some implementations, the playback device may include a processing system (e.g., processing system 500)

Date reçue / Date received 2021-11-29 and detect wake words within the audio content using a wake-word detection component (such as wake-word detection component 504 of Figure 5).

[0126] The playback device may analyze the received audio content using one or more wake word detection algorithms. Example wake word detection algorithms accept an audio recording as input and provide an indication of whether a wake word is present in the recording as output. Many first- and third-party wake word detection algorithms are known and commercially available. For instance, operators of a voice service may make their algorithm available for use in third-party devices. Alternatively, an algorithm may be trained to detect certain wake-words.

[0127] In some implementations, toe playback device may use the same or similar algorithm on the received data representing the audio content as utilized by MDs for detecting wake words in audio recorded via a microphone. In such a manner, the playback device may detect the same or similar wake words in toe audio content as a NMD would detect if the audio content was played back in audible range of the NMDs. However, given thatNMDs typically run wake word detection algorithms on microphone-recorded audio that was spoken by a wide variety of human voices in varying environmental conditions (e.g., possibly a noisy household), a wake word algorithm operating on received audio content without such variability may be even more effective in detecting wake words.

[0128] During analysis, the playback device may determine where each wake word occurs in the received audio content. After identifying the portions of the audio content that are determined to include a wake word, the playback device may note these portions of the audio content using one or more timestamps (e.g., a time stamp indicating a start time for the wake-word, and perhaps another timestamp indicating a stop time for that wake word). Ultimately, these time-stamps may be used to disable the wake-response of one or more NMDs to the wake-words corresponding to each timestamp.

[0129] In one example, the playback device may divide the received audio content into segments of known length. Then, the playback device identifies the portion(s) of the audio content— i.e., the segments— that include a wake word by identifying the segments) in which the wake word(s) were detected. For example, if each segment is 3 seconds long and the wake word was detected in the fourth segment, toe wake word is located between 9 and 12 seconds into the recording. In some instances, the playback device may separate the audio recording into overlapping segments, to avoid breaking apart a wake word into unrecognizable portions (e.g., one section representing Hey and another

Date reçue / Date received 2021-11-29 segment representing Siri). Other techniques for determining the location of a wake word within the audio recording can be utilized as well.

[0130] In some instances, the playback device runs multiple wake word detections algorithms on the received audio content simultaneously (or substantially simultaneously). As noted above, different voice services (e.g. AMAZON’S ALEXA®, APPLE’S SIRI®, or MICROSOFT’S CORTANA®) may each use a different wake word for invoking their respective voice service. Further, some voice services may allow user selection of a preferred wake word or to configure a custom wake word. To support multiple services (and/or different wake words), the playback device may run the received audio content through the wake word detection algorithm for each supported voice service in parallel. For instance, the playback device may apply, to the audio content before toe audio content is played back by toe playback device, a fust audio detection algorithm for a first voice service to detect at least one first wake word for toe first voice service and apply, to toe audio content before toe audio content is played back by toe playback device, a second audio detection algorithm for a second voice service to detect at least one second wake word for the second voice service. The playback device may apply additional audio detection algorithms to toe audio content as well, possibly for respective voice services.

c. Cause One Or More NMDs To Disable Its Respective Wake Response To The Detected One Or More Wake Words During Playback Of The Audio Content

[0131] In Figure 8, at block 806, implementation 800 involves causing one or more networked microphone devices to disable its respective wake response to toe detected one or more wake-words during playback of toe audio content. For instance, toe playback device may cause NMDs that are in audible range of toe playback device to disable their respective wake response to toe detected one or more wake-words during playback of toe audio content by toe playback device. As noted above, toe playback device may implement a processing system 500 that includes a notification component (e.g., notification component 506 of Figure 5), and use toe notification component to cause toe one or more NMDs to disable its respective wake response to toe detected one or more wake-words during playback of toe audio content by toe playback device.

[0132] As noted above, toe wake response of an NMD refers to its programmed response to detecting a wake word. When a wake response is enabled, in response to detecting a wake word, toe wake response of an NMD causes toe NMD to listen, via a microphone, for a voice command following toe particular wake word. The NMD invokes a voice service to cany out the voice 33

Date reçue / Date received 2021-11-29 command. However, when the wake response is disabled, the NMD might not listen for the voice command and will not invoke the voice service to carry out the voice command.

[0133] In some implementations, the playback device itself includes an NMD (e.g., NMD 700 is implemented within the playback device). In such implementations, the playback device disables the wake response of its own NMD to toe detected one or more wake-words while toe playback device is playing back toe audio content. For instance, an instance of processing system 500 implemented in the playback device may notify toe NMD of toe one or more wake-words and their corresponding playback times, so as to cause the NMD to disable toe wake response toe NMD to toe detected one or more wake-words. For instance, the processing system may notify toe NMD by changing a flag in RAM to disable the wake response, or by messaging toe NMD using an internal communications bus, among other examples. Then, while playing back toe audio content, toe NMD of the playback device may record, via a microphone, toe audio content being played back by toe playback device, and disable respective wake responses of the NMD to one or more wake words within the recorded audio content.

[0134] Within example implementations, toe playback device may cause all networked microphone devices within a household to disable their respective wake responses. For instance, playback device 104 shown in Figure 1 may cause NMDs 132 and 134 to disable toeir respective wake responses when playback device 104 plays back audio content containing one or more wake words. Further, if any of playback devices 102 or 106-124 implement an NMD, playback device 104 may cause these playback devices to disable toeir respective wake responses when playback device 104 plays back audio content containing the one or more wake words. Yet further, if playback device 104 itself implements an NMD, or if control device 126 or 128 implement a NMD, playback device 104 may cause these devices to disable toeir respective wake responses when playback device 104 plays back toe audio content.

[0135] Alternatively, the playback device may cause a subset of NMDs within a household to disable toeir respective wake responses. For instance, the playback device may cause NMDs witoin audible range of the playback device to disable toeir respective wake responses. Alternatively, the playback device may cause NMDs that have been associated with the playback device to disable their respective wake responses.

[0136] Audible range may be determined using any suitable technique. In some implementations, audible range is established based on a playback configuration of toe playback device. For instance, if the playback device is in a synchronous playback configuration with one or more playback devices, 34

Date reçue / Date received 2021-11-29 these playback devices may be assumed to be in audible range of the playback device. Accordingly, if any of these playback devices implement an NMD, the respective wake-responses of these playback devices are disabled. The playback device may determine that such NMDs are in audible range of the playback devices by referring to a configuration of the playback device, which may be stored in one or more state variables that are synchronized across playback devices in the household.

[0137] In other examples, audible range is established during a set-up procedure (e.g. a calibration procedure). During such a set-up procedure, NMDs within the household may be instructed to listen for an audio signal (e.g., a tone) that is played back by playback devices in the household. If an NMD can detect toe audio signal via its microphone, that NMD can be assumed to be within audible range. Playback devices within toe household may be instructed to cycle through playback of the audio signal at different volumes, so as to determine toe sets of NMDs that are in audible range of each playback device at any given volume level. Example calibration procedures may involve output of a calibration sound, which may also serve as toe audio signal to be detected by NMDs within the household.

[0138] To illustrate, during an example set-up procedure, control device 126 of Figure 1 may instruct playback devices in toe Master Bedroom Zone to output an audio signal (i.e., playback devices 122 and 124). At most volume levels, this output is detected by NMD 134. However, as the volume level is increased, other NMDs start to detect the output as well. For instance, and playback device 118 and control device 128 may each implement an NMD and detect audio signal output at relatively higher volume levels. As such, via the example set-up procedure, NMD 134 is established as being in audible range of playback devices 122 and 124 at certain volume range (e.g., 5% - 100%) while playback device 118 and control device 128 are considered is established as being in audible range of playback devices 122 and 124 at certain higher volume ranges (e.g., volume levels > 80%). This procedure can be repeated for other playback devices and NMDs within the household.

[0139] In other examples, a NMD may be paired with one or more playback devices based on a known physical proximity. For instance, referring back to Figure 1, NMD 134 may be paired with playback device 122 and/or 124 as the NMD for the Master Bedroom zone. Such pairing may be configured via a user interface on a control device, such as control device 126 or 128. As another example, NMD 132 may be paired with playback devices 104,106,108,110,112, and/or 114 on toe grounds that NMD 132 is paired with the Kitchen Zone and the Kitchen zone is known to be in physical proximity to the Dining Room and/or Living Room zone or on toe grounds that the Kitchen zone is foimed into a zone group with the Dining Room or Living Room zone. If a NMD is paired

Date reçue / Date received 2021-11-29 with one or more playback devices, the NMD may be assumed to be within audible range of these playback devices.

[0140] Other examples for determining the presence of NMDs that are in proximity to playback devices of a media playback system are described in: App. No. 15/098,867 filed on April 14, 2016, titled Default Playback Device Designation; App. No. 15/098,892 filed on April 14, 2016, titled Default Playback Devices; App. No. 15/237, 133, titled Audio Response Playback; and App. No. 15/229,855 filed on August 5,2016, titled Determining Direction of Networked Microphone Device Relative to Audio Playback Device.

[0141] As suggested above, in some cases, the playback device is configured to play back audio in synchrony with one or more additional playback devices, perhaps in a zone group, stereo pair, or surround sound configuration. Such configurations may extend the audible range of the playback device, as any NMD in audible range of the playback device or any of toe one or more additional playback devices may falsely trigger in response to wake words in audio content played back by these playback devices in synchrony. As such, if toe playback device is currently in a synchronous playback configuration with one or more additional playback devices, the playback device may disable toe respective wake responses of NMDs that are in audible range or otherwise associated with toese additional playback devices.

[0142] In some implementations, toe playback device causes toe one or more NMDs to disable its respective wake response to toe detected one or more wake words by sending, via a network interface to toe one or more NMDs, instructions that cause toe one or more NMDs to disable their respective wake responses during playback of toe received audio content. As noted above, various devices of a media playback system (e.g., control devices, playback devices, and NMDs) may be interconnected via a local area network (e.g., via a local area networked formed by wired or wireless network router 130 of Figure 1) to permit exchange of instructions and other messaging between the devices within toe household. These devices of a media playback system may each be programmed to respond to certain instructions from other devices in toe system.

[0143] In some examples, such instructions may prevent the one or more NMDs from detecting toe wake word as it is played back by toe playback device. For instance, toe playback device may instruct one or more NMDs to stop listening for wake words (e.g., to stop processing recorded audio) for one or more period of times (i.e., the periods of time corresponding to when the wake words will be played back by the playback device, perhaps notated by time-stamps). Alternatively, the playback 36

Date reçue / Date received 2021-11-29 device may instruct the one or more NMDs to disable their respective microphones temporarily (e.g., during the period of times noted above). As yet another example, the playback device may instruct the one or more NMDs to create a listening NULL in the direction of the playback device using its microphone array, so that the NMDs do not detect the wake word. Other examples are possible as well. For instance, shortly before the playback device plays a portion of the audio content containing a wake-word, the playback device may send a first message instructing the one or more NMDs to disable wake word detection. Then, shortly after die playback device plays the portion of foe audio content containing the wake-word, the playback device may send a second message instructing the one or more NMDs to enable wake word detection.

[0144] To illustrate, Figure 9 depicts example message 900, which a playback device may send to one or more NMDs to cause the one or more NMDs to disable its respective wake response to foe detected one or more wake words. Message 900 may conform to a specification, such as the IEEE 802.3 specification (which specifies the structure of an Ethernet packet and frame). As shown, message 900 includes a preamble 902, which includes a pattern of alternating bits by which devices on the network (e.g., NMDs, playback devices, and/or control devices, among others) may synchronize their receiver clocks. Message 900 also includes a start of frame delimiter (SFD) 904, which marks the end of the preamble (the first field of an Ethernet packet) and foe beginning of foe Ethernet frame portion of foe message. Message 900 also includes destination address 906 and source address 908, which indicate foe destination (e.g., a NMD) and the source (e.g., the playback device). Message 900 further includes a payload 910. The payload 910 includes instructions to cause an NMD (i.e., foe NMD indicated by the destination address 906) to disable its wake response to one or more wake words. Message 900 further includes a frame check sequence (FCS) 912, which is a cyclic redundancy check values that allows detection of corrupted data within foe frame as received.

[0145] The instructions may be transmitted using two or more Ethernet packets (e.g., two or more of message 900). For instance, foe instructions to one NMD may be divided across foe payloads of two or more instances of messages 900. Further, instructions to multiple NMDs may each be sent in one or more respective instances of message 900. Other examples are possible as well.

[0146] By way of example, Figures 10A, 10B, IOC, and 10D illustrate example instructions 1000

A, 1000B, 1OOC, and 100D, which may be transmitted in foe payload(s) of one or more messages to a NMD (e.g., payload 910 of message 900). As shown in Figure 10A, instructions 1000A includes command 1002A to cause a NMD to disable a wake response during certain time periods defined by

Date reçue / Date received 2021-11-29 time stamps 1004 A, 1006 A, 1008 A, 1010A. In some examples, time stamps 1004 A and 1006 A designate the beginning and end, respectively, of a time period during which the playback device will play back a portion of the audio content containing a first wake word. Similarly, time stamps 1008 A and 1010A may designate the beginning and end, respectively, of a time period during which the playback device will play back a portion of the audio content containing a second wake word. Instructions 1000 Λ may include further time stamps that define additional time periods. Alternatively, stamps 1004A, 1O06A, 1008 A, and 1010A may correspond toe a playback time for a particular frame of audio, a time corresponding to a system clock on the sending or receiving device; or a time corresponding to a global clock that is known to both the NMD and the playback device, among other examples.

[0147] Figure 10B shows instructions 1000B, which include a command 1002B to cause a NMD to create a listening null in certain directions defined by coordinates 1004B and 1006B. Coordinates 1004B and 1006B indicate the directions of respective playback devices relative to the NMD. For instance, referring back to Figure 1, an example instance of instructions 1O00B may include coordinates 1004B and 1006B to indicate the directions of playback devices 122 and 124 relative to NMD 134. In this example, the coordinates 1004B and 1006B may indicate to NMD 134 that playback device 122 is 0° relative to NMD 134 {i.e., directly in front of NMD 134) while playback device 122 is 45° to the left relative to NMD 134. Respective locations of devices within a household relative to one another may be pre-established by a set-up or configuration procedure.

[0148] Figures IOC and 10D show instructions 1OOOC and 100D respectively. Instructions 1OOOC include a command 1002C to cause the receiving NMD to disable wake word detection. The playback device may send such instructions shortly before playing back a portion of the audio content that includes a wake word. Instructions 100D include a command 1002D to cause the receiving NMD to arable wake word detection. The playback device may send such instructions shortly after playing back the portion of the audio content that includes the wake word.

[0149] In a further example, the one or more NMDs may detect the wake word, but the playback device instructs the one or more NMDs to suppress its wake response. For instance, the playback device may instruct the one or more NMDs to disregard wake words during certain periods of time or to disregard all audio during certain periods of time. Other examples are possible as well.

[0150] As another example, the playback device may count the number of wake words in the audio content (or in a portion of the audio content). For instance, the playback device might detect 38

Date reçue / Date received 2021-11-29 three wake words in an example audio content. As noted above, such instances may include any combination of wake words, including different wake words for different voice services. Then, the playback device may instruct the one or more NMDs in the vicinity to ignore wake words until they have detected a number of wake words equal to the count (e.g., to ignore the next three wake words).

[0151] Alternatively, the playback device causes the one or more NMDs to disable its respective wake response to the detected one or more wake words by dynamically modifying the audio content to incorporate acoustic markers in segments of the audio content. For instance, the playback device may insert (e.g., mix in) in an audio tone or other marker in the recorded audio content to designate wake words detected in the audio content. Then, NMDs can be instructed or pre-programmed to ignore an instance of a wake word if they detect the audio marker in association with the wake word (e.g., shortly before, or concurrently with the wake word). Using such a technique, NMDs in audible range of the playback device need not be pre-determined or estimated. Radier, since the acoustic markers) are played back with the audio content, NMDs that are in audible range to detect the audio content (and, as such, may be falsely triggered by this content) are also in range to detect the acoustic markers) and responsively disable their wake response. If multiple NMDs are in audible range of the playback device, each NMD that detects a wake word responsively disables its wake response to the wake word in response to detecting the associated acoustic marker,

d. Plav Back The Audio Content

[0152] In Figure 8, at block 808, implementation 800 involves playing back the audio content via one or more speakers. The playback device plays back the audio content via one or more audio transducers (e.g., speakers). In some instances, the speakers are co-located with the playback device in the same housing. Alternatively, the playback device may provide amplified audio via speaker jacks to one or more separate passive speakers. As another example, the playback device may play back the audio content by providing line-level audio to an amplifier, which then in turn provides amplified audio via speaker j acks to one or more passive speakers.

[0153] As noted above, in some instances, the playback device is configured into a synchronous playback configuration with one or more additional playback devices. In such instances, playing back the audio content involves playing back the audio content in synchrony with the one or more additional playback devices. In some playback configurations (e.g., stereo pair or surround), each playback device in the playback configuration plays back a portion of the audio content in synchrony with the other playback devices in the playback configuration.

Date reçue / Date received 2021-11-29

[0154] In some implementations, the playback device provides the audio content to one or more additional playback devices for playback to facilitate synchronous playback of that audio content with the playback device. In such implementations, the playback device may operate as a group coordinator for the synchrony group including the playback device and the one or more additional playback devices. As group coordinator, the playback device may additionally provide timing information to the one or more additional playback devices to facilitate the synchrony group scheduling synchronous playback. The playback device provides the audio content and/or the timing information via a network interface.

[0155] As noted above, in some cases, the playback device modifies the audio content to include acoustic markers. In such embodiments, if the playback device is in a synchrony group, the playback device may provide the modified audio content to other playback devices in the synchrony group. Each playback device in the synchrony group may then play back the modified audio content in synchrony with the other playback devices in the group.

[0156] To illustrate, in one example, playback devices 114 and 122 and 124 are in a zone group (i.e., a Kitchen + Master Bedroom zone group) that is configured to play back audio content in synchrony. After detecting wake words in audio content designated for playback by the zone group, playback device 114 may modify the audio content to include acoustic markers to designate the wake words in the audio content. Playback device 114 may then provide the modified audio content to playback device 122 and/or 124, so as to facilitate synchronous playback of the modified audio content.

IV. Example Techniques For A NMD To Disable A Wake-Response

[0157] As discussed above, embodiments described herein may involve disabling a wake response. Figure 11 illustrates an example implementation 1100 by which a NMD disables its wake response to one or more detected wake words.

a. Receive Data Representing Audio Content For Playback

[0158] At block 1102, implementation 1100 involves receiving data representing recorded audio content. For instance, NMD may receive audio content for playback by a playback device. Example NMDs include any of NMDS 132 and 134 shown in Figure 1, which may be implemented as NMD 700 of Figure 7, for example. Example playback devices include any of playback devices 102,104, 106,108,110,112,114,116, 118,120,112, and 124 shown in Figure 1, which may be implemented

Date reçue / Date received 2021-11-29 as represented by playback device 200 of Figure 2, for instance. Further example NMDs may include any of these playback devices and/or control devices 126 and 128, as such devices may implement an

NMD in addition to their functionality as a playback or control device. The NMD may include a processing system (e.g., processing system 500) and receive Ae data representing Ae audio content using an audio input/output component (such as audio input/output component 502 of Figure 5).

[0159] The NMD may receive Ae audio content via an input interface, which may be a wired or wireless netwoik interface or an analog or digital line-in interface, among oAer examples. For instance, Ae NMD may receive Ae audio content from a network source via a network interface over one or more types of networks, such as WANs, LANs, and PANs, among oAer possibilities.

[0160] The NMD may receive Ae data representing Ae audio content from a local or remote audio source. For instance, Ae NMD may receive Ae audio content from a local media server or oAer device on a local area network, from a medium (such as a CD, DVD, Blu-Ray, flash memory, or hard drive) Aat is read by Ae NMD or by anoAer device in communication wiA Ae NMD (e.g., a playback device Aat is connected to Ae NMD over a local area network via a network interface), or from data storage on Ae NMD itself.

[0161] The NMD may receive Ae audio content as an audio content stream, perhaps from one or more cloud serveis. For instance, Ae NMD may retrieve an audio content stream from a URL via a network interface. Alternatively, Ae NMD may receive Ae audio content from a line-in interface on Ae NMD or on anoAer device in communication wiA Ae NMD (e.g., a playback device Aat is connected to Ae NMD over a local area network via a netwoik interface).

[0162] In some cases, Ae NMD may receive au Ao content in analog format, perhaps via an analog line-in interface. In such instances, Ae NMD digitizes Ae analog audio (e.g., using a software or hardware-based analog-to-digital converter) into a format suitable for processing. Alternatively, a device in communication wiA Ae NMD (e.g., a playback device) may receive audio content in analog format, digitize toe audio content, and transmit data representing toe audio content to toe playback device.

[0163] As noted above, the received audio content is designed for playback by a playback device.

For instance, a control device (such as control device 126 or 128 of Figure 1) may instruct a playback device to play back certain audio content, perhaps by causing that content to be placed in a playback queue of the playback device. Placing an audio track or other audio content into such a queue causes

Date reçue / Date received 2021-11-29 the playback device to retrieve the audio content, perhaps after playback is initiated via a control on the control device or on the playback device itself (e.g., a Play/Pause button). The NMD may have access to this queue (e.g., the contents of the queue may be shared with the NMD via a LAN or other network). Given such access, the NMD may retrieve the audio content from the local or remote audio source by directing an audio content stream to the NMD via a network interface or by directing audio content to the NMD via an analog or digital line-in interface, among other examples.

[0164] In some cases, the received audio content is designed for playback by two or more playback devices. For instance, two or more playback devices may be configured into a synchrony group (e.g., a zone group, stereo pair, or surround sound configuration). A particular audio content may be designated for playback by this synchrony group.

[0165] Within examples, processing system 500 may store at least a portion of the received audio content in memory. For instance, processing system 500 may buffer received audio content in a firstin-first-out buffer (e.g., a circular buffer). In such implementations, portions of the received audio are stored in the buffer when they are received, and are removed as they are processed to which enables the playback device to determine if the received audio content contains wake words.

b. Detect. In The Audio Content. One Or More Wake Words

[0166] In Figure 1 1, at block 1 104, implementation 1 100 involves detecting, in the audio content, one or more wake-words before the audio content is played back by the playback device. For instance, the NMD may analyze the received data representing the audio content to determine if wake words for any voice services are represented in the audio content, such that when the audio content is played back, the wake words will be played audibly. As noted above, in some implementations, the NMD may include a processing system (e.g., processing system 500) and detect wake words within the audio content using a wake-word detection component (such as wake-word detection component 504 of Figure 5).

[0167] The NMD may analyze the received audio content using one or more wake word detection algorithms. Example wake word detection algorithms accept an audio recording as input and provide an indication of whether a wake word is present in the recording as output. Many first- and third-party wake word detection algorithms are known and commercially available. For instance, operators of a voice service may make their algorithm available for use in third-party devices. Alternatively, an algorithm may be trained to detect certain wake-words. [0168] In regular operation, a NMD will

Date reçue / Date received 2021-11-29 listen for sound (e.g., human voices) in a household or other environment via a microphone and run audio recordings of that sound through a wake word detection algorithm to detect if the sound contained a wake word. In this process, the NMD may use the same or similar algorithm as used by the NMD for detecting wake words spoken by human voices. However, instead of the input to the algorithm being audio recorded via a microphone, the input is audio content for playback by a playback device. In such a manner, the NMD may detect the same or similar wake words in the audio content as a NMD would detect if the audio content was played back in audible range of the NMDs. However, given that NMDs typically run wake word detection algorithms on microphone-recorded audio that was spoken by a wide variety of human voices in varying environmental conditions (e.g., possibly a noisy household), a wake word algorithm operating on received audio content without such variability may be even more effective in detecting wake words.

[0169] During analysis, the NMD may determine where each wake word occurs in the received audio content. After identifying the portions of the audio content that are determined to include a wake word, the NMD may note these portions of the audio content using one or more timestamps (e.g., a time stamp indicating a start time for the wake-word, and perhaps another timestamp indicating a stop time for that wake word). Ultimately, these time-stamps may be used to disable the wake-response of the NMDs to the wake-words corresponding to each time-stamp.

[0170] In one example, the NMD may divide the received audio content into segments of known length. Then, the NMD may identify the portion(s) of the audio content— i.e., the segments— that include a wake word by identifying the segments) in which the wake word(s) were detected. For example, if each segment is 4 seconds long and the wake word was detected in the sixth segment, the wake word is located between 20 and 24 seconds into the recording. In some instances, the NMD may separate the audio recording into overlapping segments, to avoid breaking apart a wake word into unrecognizable portions (e.g., one section representing Hey and another segment representing Alexa”). Other techniques for determining the location of a wake word within the audio recording can be utilized as well.

[0171] In some instances, the NMD runs multiple wake word detections algorithms on the received audio content concurrently. As noted above, different voice services (e.g. AMAZON'S ALEXA®, APPLE'S SHU®, or MICROSOFT'S CORTANA®) may each use a different wake word for invoking their respective voice service. Further, each voice service may support multiple wake words and/or custom wake words. To an effort to support multiple voice services, the NMD may run

Date reçue / Date received 2021-11-29 the received audio content through the wake word detection algorithm for each supported voice service in parallel, so as to detect different wake words that might be represented in the audio content. For instance, the NMD may apply a first audio detection algorithm for a first voice service to detect at least one first wake word for the first voice service and apply a second audio detection algorithm for a second voice service to detect at least one second wake word for the second voice service. Before the audio content is played back by the playback device, the NMD may apply additional audio detection algorithms to the audio content as well, possibly for respective voice services.

c. Disable Wake Response To The Detected One Or More Wake Words During Playback Of The Audio Content

[0172] In Figure 11, at block 1106, implementation 1100 involves disabling a wake response to the detected one or more wake-words during playback of the audio content. For instance, the NMD may disable its wake response to the one or more wake-words that were detected in the audio content when the audio content is played back audibly by the playback device.

[0173] As noted above, the wake response of an NMD refers to its programmed response to detecting a wake word. When a wake response is enabled, in response to detecting a wake word, the wake response of an NMD causes the NMD to listen, via a microphone, for a voice command following tiie particular wake word. The NMD invokes a voice service to carry out tiie voice command. However, when the wake response is disabled, the NMD might not listen for the voice command and will not invoke the voice service to carry out the voice command.

[0174] In some implementations, the NMD disables its wake response by preventing the NMD from detecting the wake word as it is played back by the playback device. For instance, the NMD may stop listening for wake words (e.g., to stop processing recorded audio) for one or more period of times (i.e., the periods of time corresponding to when the wake words will be played back by the playback device, perhaps notated by time-stamps). Alternatively, the NMD may disable its microphone temporarily (e.g., during the period of times noted above). As yet another example, the NMD may create a listening NULL in the direction of the playback device using its microphone array, so that the NMD does not detect the wake word. Other examples are possible as well.

[0175] In further examples, 1he NMD detects the wake word as it is played back by the playback device, but suppresses its wake response to that detected wake word. For instance, the NMD may

Date reçue / Date received 2021-11-29 disregard wake words during periods of time or to disregard all audio during certain periods of time. Other examples are possible as well.

[0176] As another example, the NMD may count the number of wake words in the audio content (or in a portion of the audio content). For instance, the NMD might detect three wake words in an example audio content. As noted above, such instances may include any combination of wake words, including different wake words for different voice services. Then, the NMD may then disable its wake response until it detected a number of wake words equal to the count (e.g., by ignoring the next three wake words).

[0177] Alternatively, the NMD disable its respective wake response to the detected one or more wake words by modifying the audio content to incorporate acoustic markers in segments of the audio content. For instance, the NMD may insert (e.g., mix in) in an audio tone or other maiker in the recorded audio content to designate wake words detected in the audio content. Then, given that the NMD is programmed to disable its wake response in response to detecting such an audio maiker, the NMD will automatically suppress the wake response when detecting the wake words in the audio content played back by the playback device.

[0178] In some examples, the NMD may cause one or more additional networked microphone devices to disable their respective wake responses to the detected wake word(s) when the wake word(s) are played back by the playback device. For instance, referring to Figure 1, NMD 132 may cause NMD 134 to disable its wake response. Moreover, any of the playback devices and/or control devices in the household may implement a NMD, and NMD 132 may also disable the wake response of any of these playback devices.

[0179] The NMD may disable a particular set of NMDs within a household. In some cases, the set of NMDs that have their wake responses disabled is based on a zone or zone group configuration of a media playback system. For instance, if the NMD is associated with a particular zone, (e.g., if NMD 132 is associated with the Kitchen zone), the NMD may cause the respective wake responses of any NMDs that are also associated with that same zone to be disabled. These NMDs can include various devices that implement NMDs (e.g., playback devices), as well as dedicated NMDs. Further, if the particular zone that the NMD is associated with is joined with one or more additional zones in a zone group, the NMD may cause the

Date reçue / Date received 2021-11-29 respective wake responses of any NMDs that are also associated with the one or more additional zone to be also disabled. As indicated above, an association may be created between a NMD and a zone of a media playback system, peihaps to facilitate co-operation in a specific room of a household (e.g., a

Kitchen zone).

[0180] Alternatively, the particular additional NMDs that have their wake responses disabled is based on the audible range of the playback device(s) that are playing back the audio content that includes the wake words. Audible range may be determined using any suitable technique. In some implementations, audible range is established based on an association of 1he NMD with one or more zones, as indicated above. In other examples, audible range is established during a set-up procedure (e.g. a calibration procedure), as described above in section III. Audible range established by zone configurations and/or set-up procedures can be stored as one or more state variables and shared among devices within a network (e.g., a LAN established by router 130 in the household shown in Figure 1). By having access to such information, the NMD can determine the set of NMDs that will be in audible range of the playback device(s) that will be playing back the audio content, and cause the respective wake responses of these set of NMDs to be disabled.

[0181] To illustrate, in one example, NMD 132 in Figure 1 detects one or more wake-words in a given audio content designed for playback by playback device 1 14 in the Kitchen zone. Accordingly, NMD 132 disables its wake response to these wake words. Since playback device 1 14 is also an NMD, NMD 132 disables the wake response of playback device 1 14. Moreover, since the Kitchen zone is in a zone group with the Dining Room zone, NMD 132 also disables the wake response of playback device 1 12, which is also an NMD, so that when the audio content is played back in the Dining Room zone in synchrony with the Kitchen zone, the NMD of playback device 112 does not falsely trigger.

[0182] In another example, NMD 134 in Figure 1 detects one or more wake-words in a given audio content designed for playback by playback devices 122 and 124 in the Master Bedroom zone. Accordingly, NMD 134 disables its wake response to these wake words. Since playback device 116 implements an NMD and has been pre-established to be in audible range of playback devices 122 and 124 at their current volume level, NMD 134 also disables the wake response of playback device 116. NMD 134 is aware that playback device 1 16 is in audible range of playback devices 122 and 124 at their current volume level from one or more state variables shared with NMD 134 via a LAN created by router 130. Such state variables indicate to NMD 134 that status of various aspects of media

Date reçue / Date received 2021-11-29 playback system 100, such as the current playback configuration of playback devices 122 and 124 (e.g., stereo pair), their current volume level, and which NMDs have been determined to be within audible range of these playback devices in this playback configuration and at this volume level.

[0183] The NMD may cause the one or more additional NMDs to disable their respective wake responses using any suitable technique. The NMD may implement a processing system 500 that includes a notification component (e.g., notification component 506 of Figure 5), and use the notification component to cause a set of one or more NMDs to disable its respective wake response to the detected one or more wake-words during playback of the audio content by the playback device.

[0184] In some implementations, foe NMD causes foe one or more additional NMDs to disable their respective wake response to foe detected one or more wake words by sending, via a network interface to foe one or more NMDs, instructions that cause foe one or more NMDs to disable their respective wake responses during playback of foe received audio content. As noted above, various devices of a media playback system (e.g., control devices, playback devices, and NMDs) may be interconnected via a local area network (e.g., via a local area networked formed by wired or wireless network router 130 of Figure 1) to permit exchange of instructions and other messaging between foe devices within foe household. These devices of a media playback system may each be programmed to respond to certain instructions from other devices in foe system. Example messages and instructions are described above in connection with Figure 9 and 10A, 10B, IOC, and 10D.

[0185] Alternatively, foe NMD causes foe one or more NMDs to disable its respective wake response to foe detected one or more wake words by modifying foe audio content to incorporate acoustic markers in segments of foe audio content. Using such a technique, NMDs in audible range of foe playback device need not be pre-determined or estimated. Rather, since foe acoustic markers) are played back with foe audio content, NMDs that are in audible range to detect foe audio content (and, as such, may be falsely triggered by this content) are also in range to detect foe acoustic markers) and responsively disable their wake response. If multiple NMDs are in audible range of foe NMD, each NMD that detects a wake word responsively disables its wake response to the wake word in response to detecting foe associated acoustic marker.

[0186] In some implementations, such as those in which foe NMD modifies foe audio content, foe NMD provides foe audio content to foe playback device. In such instances, foe NMD may operate as an intermediary between the source of audio content and foe playback device. Transmitting foe audio content to foe playback device may cause foe playback device to play back foe audio content, 47

Date reçue / Date received 2021-11-29 as the playback device may be configured to play back received audio content. The NMD may provide the audio content to the playback device via any suitable communication interface, such as a network interface. If multiple playback devices are configured to play back the audio content, the NMD may provide the audio content to all of the playback devices, or the NMD may transmit the audio content to a subset of the playback devices (e.g., a group coordinator) which then distributes the audio content to other playback devices in the group, perhaps along with timing information to schedule synchronous playback.

[0187] To illustrate, in one example, playback devices 112 and 124 are in a zone group (i.e., a Kitchen + Dining Room zone group) that is configured to play back audio content in synchrony. After detecting wake words in audio content designated for playback by the zone group, NMD 132 may modify the audio contentto include acoustic markers to designate the wake words in the audio content. Playback device 132 may then provide the modified audio content to playback device 112 and/or 114, so as to facilitate synchronous playback of the modified audio content, d. Detect The Played Back Audio Content

[0188] At block 1108, implementation 1100 involves detecting the played back audio content via a microphone. For instance, while the playback device(s) are playing back the audio content that includes the one or more detected wake words, the NMD may detect the played back audio content via a microphone. In a configuration in which the wake response of the NMD is enabled, detecting the portions of foe played back audio content that include wake words would trigger foe wake response of foe NMD. However, since the NMD disabled foe wake response for foe one or more wake words in foe audio content, foe wake response is not triggered.

[0189] In some implementations, a playback device implements foe NMD. In such examples, foe playback device may play back foe received audio content via one or more speakers. In some instances, foe speakers are co-located with foe NMD in foe same housing. Alternatively, the playback device may provide amplified audio via speaker jacks to one or more separate passive speakers. As another example, foe playback device may play back foe audio content by providing line-level audio to an amplifier, which then in turn provides amplified audio via speaker] acks to one or more passive speakers.

[0190] In some instances, an NMD is configured into a synchronous playback configuration with one or more additional playback devices. In such instances, playing back foe audio content involves playing back foe audio content in synchrony with foe one or more additional playback devices. In 48

Date reçue / Date received 2021-11-29 some playback configurations (e.g., stereo pair or surround), each playback device in the playback configuration plays back a portion of the audio content in synchrony with the other playback devices in the playback configuration.

[0191] As noted above, in some implementations, the NMD provides the audio content to one or more playback devices for playback. In some examples, the NMD provides the audio content to the one or more playback devices to facilitate synchronous playback of that audio content with the NMD. In such implementations, the NMD may operate as a group coordinator for the synchrony group including the NMD and the one or more additional playback devices. As group coordinator, the NMD may additionally provide timing information to the one or more additional playback devices to facilitate the synchrony group scheduling synchronous playback. The playback device provides the audio content and/or the timing information via a network interface.

V. Example Techniques For A Computing System To Disable A Wake-Response

[0192] As discussed above, embodiments described herein may involve disabling a wake response. Figure 12 illustrates an example implementation 1200 by which a computing system disables a wake response of one or more NMDs to one or more wake words in audio content. In various embodiments, the computing system may be a cloud server. Alternatively, the computing system may be a local processing device (e.g., a device that is connected to the same LAN as a media playback system). The computing system may implement a playback device or a NMD.

a. Receive Data Representing Recorded Audio Contait

[0193] At block 1202, implementation 1200 involves receiving data representing recorded audio content. For instance, a computing system may receive audio content for playback by a playback device. Example playback devices include any of playback devices 102,104,106,108,1 10,1 12,1 14,1 16,1 18,120,1 12, and 124 shown in Figure 1, which may be implemented as represented by playback device 200 of Figure 2, for instance. The processing system may include a processing system (e.g., processing system 500) and receive the data representing the audio content using an audio input/output component (such as audio input/output component 502 of Figure 5). The computing system may receive the audio content using any suitable technique, such as the techniques discussed above in sections Π, ΠΙ and IV.

b. Detect In The Audio Content One Or More Wake Words

Date reçue / Date received 2021-11-29

[0194] In Figure 12, at block 1204, implementation 1200 involves detecting, in Ae audio content, one or more wake-words before Ae audio content is played back by Ae playback device. For instance, Ae computing system may analyze Ae received data representing Ae audio content to determine if wake words for any voice services are represented in Ae audio content, such Aat when Ae audio content is played back, Ae wake words will be played audibly. As noted above, in some implementations, Ae computing system may include a processing system (e.g., processing system 500) and detect wake words wi Ain Ae audio content using a wake-word detection component (such as wake-word detection component 504 of Figure 5). The computing system may detect Ae wakewords using any suitable technique, such as Ae techniques discussed above in sections Π, III and IV.

c. Cause One Or More MDs To Disable Its Respective Wake Response To The Detected One Or More Wake Words During Playback Of The Audio Content

[0195] In Figure 12, at block 1206, implementation 1200 involves causing one or more networked microphone devices to disable its respective wake response to Ae detected one or more wake-words during playback of Ae audio content. For instance, Ae computing system may cause NMDs Aat are in audible range of Ae playback device to disable Aeir respective wake response to Ae detected one or more wake-words during playback of Ae audio content by Ae playback device. As noted above, Ae computing system may implement a processing system 500 Aat includes a notification component (e.g., notification component 506 of Figure 5), and use Ae notification component to cause Ae one or more NMDs to disable its respective wake response to Ae detected one or more wake-words during playback of Ae audio content by Ae playback device. The computing system may cause Ae one or more NMDs to disable its respective wake response to Ae detected one or more wake-words during playback of Ae audio content using any suitable technique, such as Ae techniques discussed above in sections II, III and IV.

VI. Example Techniques To Suppress A Wake Response

[0196] As discussed above, embodiments described herein may involve suppressing a wake response. Figure 13 illustrates an example implementation 1300 by which a NMD disables a wake response.

a. Receive Instruction To Disable Wake Response Of A NMD To One Or More Wake Words

[0197] At block 1302, implementation 1300 involves receiving an instruction to disable a wake response of an NMD to one or wake words. For instance, an NMD (e.g., NMD 132) may receive an

Date reçue / Date received 2021-11-29 instruction from another NMD, a playback device, a computing system, or any other device. The instruction causes the NMD to disable its wake response to one or more wake words that are represented in certain audio content that has been designated for playback by one or more playback devices.

[0198] In some implementations, the received instruction to disable toe wake response of the NMD to one or wake words is implicit For example, the NMD may be instructed to not detect the wake word as it is played back by the playback device, perhaps by instructing toe NMD to stop listening for wake words, by disabling the microphone array of the NMD for a period of time, or by creating a listening NULL in the direction of the playback device, among other examples. Alternatively, the NMD may detect the wake word, but be instructed to suppress its programmed wake response to invoke a voice service in response to detecting the wake word, perhaps by disregarding wake words during certain periods of time or by disregarding all audio during certain periods of time. The NMD may be instructed using any suitable instruction, such as those discussed above in sections II, ΙΠ and IV.

[0199] Alternatively, the received instruction is implicit. For instance, as described above, audio content may be modified to include acoustic markers designating wake words. In such implementations, the received instruction may be in the form of an acoustic marker. In some cases, the received instruction may be an instruction to disable the NMD's wake response when an acoustic marker is detected.

b. Detect Audio Content Being Played Back By One Or More Playback Devices

[0200] In Figure 13, at block 1304, implementation 1300 involves detecting audio content being played back by one or more playback devices. For instance, the NMD may detect audio content being played back by a single playback device via a microphone. Alternatively, the NMD may detect audio content being played back by two or more devices (e.g., in synchrony), c. Determine That The Detected Audio Content Includes One Or More Wake Words

[0201] In Figure 13, at block 1306, implementation 1300 involves determining that the detected audio content includes one or more wake words. For instance, the NMD may determine that the detected audio content includes one or more wake words by running the detected audio content through one or more wake word detection algorithms. In some instances, the NMD may run the detected audio content through multiple wake word detection algorithms (e.g., wake word detection

Date reçue / Date received 2021-11-29 algorithms for different wake words, possibly for different voice services). Example wake word detection algorithms are described throughout this disclosure.

d. Disable The Wake Response Of The NMD To The One Or More Wake Words In The Detected Audio Content

[0202] In Figure 13, at block 1308, implementation 1300 involves disabling the wake response of the NMD to the one or more wake words in the detected audio content. As noted above, the wake response of an NMD refers to its programmed response to detecting a wake word. When a wake response is enabled, in response to detecting a wake word, the wake response of an NMD causes the NMD to listen, via a microphone, for a voice command following the particular wake word. The NMD invokes a voice service to carry out the voice command. However, when the wake response is disabled, the NMD might not listen for the voice command and will not invoke the voice service to cany out the voice command.

VII. Conclusion

[0203] The description above discloses, among other things, various example systems, methods, apparatus, and articles of manufacture including, among other components, firmware and/or software executed on hardware. It is understood that such examples are merely illustrative and should not be considered as limiting. For example, it is contemplated that any or all of the firmware, hardware, and/or software aspects or components can be embodied exclusively in hardware, exclusively in software, exclusively in firmware, or in any combination of hardware, software, and/or firmware. Accordingly, the examples provided are not the only way(s) to implement such systems, methods, apparatus, and/or articles of manufacture.

[0204] (Feature 1) A method comprising receiving, via a playback device, data representing audio content for playback by a playback device; before the audio content is played back by the playback device, detecting, in the audio content, one or more wake words for one or more voice services; causing one or more networked microphone devices to disable its respective wake response to the detected one or more wake words during playback of the audio content by toe playback device, wherein, when enabled, the wake response of a given networked microphone device to a particular wake word causes toe given networked microphone device to listen, via a microphone, for a voice command following toe particular wake word; and playing back toe audio content via one or more speakers.

Date reçue / Date received 2021-11-29

[0205] (Feature 2) The method of feature 1, wherein the playback device comprises the given networked microphone device, and wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises: while playing back the audio content, recording, via the microphone, the audio content being played back; and disabling respective wake responses of the given networked microphone device to the one or more wake words within the recorded audio content.

[0206] (Feature 3) The method of feature 1, wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises: sending, via the network interface to the one or more networked microphone devices, instructions that cause the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device.

[0207] (Feature 4) The method of feature 2, wherein the one or more networked microphones devices are a subset of networked microphone devices in a household, and wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises: determining that the one or more networked microphone devices are in audible vicinity of the audio content; and in response to determining that the one or more networked microphones are in audible vicinity of the audio content, sending the instructions that cause the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device.

[0208] (Feature 5) The method of feature 4, wherein the one or more networked microphone devices comprise respective playback devices, and wherein determining that the one or more networked microphones devices are in audible vicinity of the audio content comprises determining that the one or more networked microphone devices are in a synchronous playback configuration with the playback device.

[0209] (Feature 6) The method of feature 4, wherein determining that the one or more networked microphones devices are in audible vicinity of the audio content comprises determining that the one or more networked microphone devices are in audible vicinity of the playback device.

Date reçue / Date received 2021-11-29

[0210] (Feature 7) The method of feature 1, wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises: before playing back the audio content, modifying the audio content to incorporate acoustic markers in segments of the audio content that represent respective wake words, wherein detecting the acoustic markers causes the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device.

[0211] (Feature 8) The method of feature 1, wherein detecting the one or more wake words comprises applying multiple wake-word detection algorithms to the audio content, wherein the multiple wake-word detection algorithms comprise a first wake-word detection algorithm for a first voice service and a second wake-word detection algorithm for a second voice service, and wherein applying multiple wake-word detection algorithms to the audio content before the audio content is played back by the playback device comprises: applying, to the audio content before the audio content is played back by the playback device, the first audio detection algorithm for the first voice service to detect at least one first wake word for the first voice service; and applying, to the audio content before the audio content is played back by the playback device, the second audio detection algorithm for the second voice service to detect at least one second wake word for the second voice service, wherein the second wake word is a different word than the first wake word,

[0212] (Feature 9) The method of feature 1, wherein the one or more or more networked microphone devices comprise a first networked microphone device and a second networked microphone device, and wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises: causing the first networked microphone device to disable its respective wake response to the detected at least one first wake word; and causing the second networked microphone device to disable its respective wake response to the detected at least one second wake word.

[0213] (Feature 10) The method of feature 1, wherein detecting, in the audio content, one or more wake words for one or more voice services comprises detecting multiple instances of a particular wake word in the audio content, and wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises causing the one or more networked microphone

Date reçue / Date received 2021-11-29 devices to disable their respective wake responses until each networked microphone device has detected a number of wake words equal to a number of the multiple instances of the particular wake word detected in the audio content

[0214] (Feature 11) A tangible, non-transitory computer-readable medium having stored therein instructions executable by one or more processors to cause a device to perform the method of any of features 1-10.

[0215] (Feature 12) A device configured to perform the method of any of features 1-10.

[0216] (Feature 13) A media playback system configured to perform the method of any of features 1-10.

[0217] (Feature 14) A method comprising: receiving, via a networked microphone device, data representing audio content for playback by a playback device; before the audio content is played back by the playback device, detecting, in the audio content, one or more wake words for one or more voice services; disabling a wake response of the networked microphone device to the detected one or more wake words during playback of the audio content by die playback device, wherein, when enabled, the wake response of the networked microphone device to a particular wake word causes the networked microphone device to listen, via a microphone, for a voice command following ihe particular wake word; and while the playback device is playing back the audio content, detecting the played back audio content via the microphone.

[0218] (Feature 15) The method of feature 14, further comprising transmitting, to the playback device via the network interface, the data representing the audio content to cause the playback device to play back the audio content.

[0219] (Feature 16) The method of feature 15, wherein disabling the wake response of the networked microphone device to the detected one or more wake words during playback of the audio content by the playback device comprises: before transmitting the data representing the audio content to the playback device, modifying the audio content to incorporate acoustic markers in segments of the audio content that represent respective wake words, wherein detecting the acoustic markers causes the networked microphone device to disable its respective wake responses to the one or more wake words during playback of the audio content by the playback device.

Date reçue / Date received 2021-11-29

[0220] (Feature 17) The method of feature 14, further comprising causing one or more additional networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device.

[0221] (Feature 18) The method of feature 17, wherein causing the one or more additional networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises: sending, via the network interface to the one or more additional networked microphone devices, instructions that cause the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device.

[0222] (Feature 19) The method of feature 17, wherein the one or more additional networked microphones devices are a subset of networked microphone devices in a household, and wherein causing the one or more additional networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises: determining that the one or more networked microphones are in audible vicinity of the audio content; and in response to determining that the one or more networked microphones are in audible vicinity of the audio content, sending the instructions that cause the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device.

[0223] (Feature 20) The method of feature 19, wherein the one or more networked microphone devices comprise respective playback devices, and wherein determining that the one or more networked microphones devices are in audible vicinity of the audio content comprises determining that that the one or more networked microphone devices are in a synchronous playback configuration with the playback device.

[0224] (Feature 21) The method of feature 14, wherein determining that the one or more networked microphones devices are in audible vicinity of the audio content comprises determining that the one or more networked microphone devices are in audible vicinity of the playback device.

[0225] (Feature 22) The method of feature 14, wherein detecting the one or more wake words comprises applying multiple wake-word detection algorithms to the audio content, wherein the multiple wake-word detection algorithms comprise a first wake-word detection algorithm for a first voice service and a second wake-word detection algorithm for a second voice service, and wherein

Date reçue / Date received 2021-11-29 applying multiple wake-word detection algorithms to the audio content before the audio content is played back by the playback device comprises: applying, to the audio content before the audio content is played back by the playback device, the first audio detection algorithm for the first voice service to detect at least one first wake word for the first voice service; and applying, to the audio content before the audio content is played back by the playback device, the second audio detection algorithm for the second voice service to detect at least one second wake word for the second voice service, wherein the second wake word is a different word than the first wake word.

[0226] (Feature 23) The method of feature 14, wherein the networked microphone device comprises the playback device, and wherein the method further comprises playing back the audio content via one or more speakers.

[0227] (Feature 24) A tangible, non-transitoiy computer-readable medium having stored therein instructions executable by one or more processors to cause a device to perform the method of any of features 14-23.

[0228] (Feature 25) A device configured to perform the method of any of features 14-23.

[0229] (Feature 26) A media playback system configured to perform the method of any of features 14-23.

[0230] (Feature 27) A method comprising: receiving, via a computing system, receiving, via an interface of the computing system, audio content for playback by one or more playback devices; before the audio content is played back by the playback device, detecting, in the audio content, one or more wake words for one or more voice services; and causing one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device, wherein, when enabled, the wake response of a given networked microphone device to a particular wake word causes the given networked microphone device to listen, via a microphone, for a voice command following the particular wake word.

[0231] (Feature 28) The method of feature 27, wherein causing the one or more networked microphone devices to di sable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises: sending, via the netwoik interface to the one or more netwotked microphone devices, instructions that cause the one or more

Date reçue / Date received 2021-11-29 networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device.

[0232] (Feature 29) The method of feature 28, wherein sending the instructions that cause the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of die audio content by die playback device comprises: sending instructions that cause the one or more networked microphone devices to disable their respective wake responses during one or more time periods corresponding to when the one or more playback devices will play back segments of the audio content that represent respective wake words.

[0233] (Feature 30) The method of feature 28, wherein sending die instructions that cause the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device comprises: sending instructions that cause the one or more networked microphone devices to disable their respective microphones during one or more time periods corresponding to when the one or more playback devices will play back segments of the audio content that represent respective wake words.

[0234] (Feature 31 ) The method of feature 28, wherein the computing system detected a particular number of wake words in the audio content, and wherein sending the instructions that cause the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device comprises: sending instructions that cause the one or more netwoiked microphone devices to disable their respective wake responses until the one or more networked microphone devices have detected a number of wake words equal to the particular number of wake words detected in the audio content.

[0235] (Feature 32) The method of feature 28, wherein the one or more networked microphones devices are a subset of networked microphone devices in a household, and wherein causing the one or more networked microphone devices to disable 1heir respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises: determining that the one or more networked microphone devices are in audible vicinity of the audio content; and in response to determining that the one or more networked microphones are in audible vicinity of the audio content, sending the instructions that cause the one or more netwoiked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device.

Date reçue / Date received 2021-11-29

[0236] (Feature 33) The method of feature 32, wherein the one or more networked microphone devices comprise respective playback devices, and wherein determining that the one or more networked microphones devices are in audible vicinity of the audio content comprises determining that the one or more networked microphone devices are in a synchronous playback configuration with the playback device.

[0237] (Feature 34) The method of feature 32, wherein determining that the one or more networked microphones devices are in audible vicinity of the audio content comprises determining that the one or more networked microphone devices are in audible vicinity of the playback device.

[0238] (Feature 35) The method of feature 27, wherein causing the one or more networked microphone devices to disable their respective wake responses to the detected one or more wake words during playback of the audio content by the playback device comprises: before the one or more playback devices play back the audio content, modifying the audio content to incorporate acoustic markers in segments of the audio content that represent respective wake words, wherein detecting the acoustic markers causes the one or more networked microphone devices to disable their respective wake responses to the one or more wake words during playback of the audio content by the playback device; and transmitting the modified audio content to at least one of the one or more playback devices for playback by the one or more playback devices.

[0239] (Feature 36) The method of feature 35, wherein receiving the audio content for playback by one or more playback devices comprises one of: (a) receiving, via a network interface of the interface, data representing the audio content or (b) receiving, via an analog interface of the interface, an analog signal representing the audio content.

[0240] (Feature 37) The method of feature 27, wherein the computing system comprises a particular playback device of the one or more playback devices, and wherein the operations further comprise playing back the audio content

[0241] (Feature 38) The method of feature 27, wherein the computing system comprises a particular networked microphone device of the one or more networked microphone device, and wherein the operations further comprise detecting, via a microphone, the audio content being playback back by the one or more playback devices.

Date reçue / Date received 2021-11-29

[0242] (Feature 39) A tangible, non-transitory computer-readable medium having stored therein instructions executable by one or more processors to cause a device to perform the method of any of features 27-38.

[0243] (Feature 40) A device configured to perform the method of any of features 27-38.

[0244] (Feature 41) A media playback system configured to perform the method of any of features 27-38.

[0245] (Feature 42) A method comprising: receiving, via a networked microphone device, an instruction to disable a wake response of die networked microphone device to one or more wake words, wherein, when enabled, the wake response of the networked microphone device to a given wake word causes the networked microphone device to listen, via the microphone, for a voice command following the given wake word; detecting, via the microphone, audio content being played back by one or more playback devices; determining that die detected audio content includes one or more wake words; and in response to the received instruction, disabling the wake response of the networked microphone device to the one or more wake words in the detected audio content.

[0246] (Feature 43) The method of feature 42, wherein receiving the instruction to disable the wake response of the networked microphone device to the one or more wake words comprises: receiving an instruction to disable the wake response during one or more time periods corresponding to when the one or more playback devices will play back segments of the audio content corresponding to respective detected wake words.

[0247] (Feature 44) The method of feature 42, wherein receiving the instruction to disable the wake response of the networked microphone device to the one or more wake words comprises: receiving an instruction to disable the microphone during one or more time periods corresponding to when the one or more playback devices will play back segments of the audio content corresponding to respective detected wake words.

[0248] (Feature 45) The method of feature 42, wherein receiving the instruction to disable the wake response of the networked microphone device to the one or more wake words comprises: receiving an instruction to disable the wake response when consecutive wake words are detected until the networked microphone device has detected a number of wake words equal to a particular number of wake words.

Date reçue / Date received 2021-11-29

[0249] (Feature 46) The method of feature 42, wherein receiving the instruction to disable the wake response of the networked microphone device to the one or more wake words comprises receiving an instruction to disable the wake response when an acoustic marker is detected, and wherein disabling the wake response of the networked microphone device to the one or more wake words in the detected audio content comprises: detecting acoustic markers in the detected audio content corresponding to respective detected wake words; and disabling the wake response in response to detecting each acoustic marker.

[0250] (Feature 47) The method of feature 42, wherein determining that the detected audio content includes one or more wake words comprises applying one or more wake-word detection algorithms to the detected audio content.

[0251 ] (Feature 48) A tangible, non-transitoiy computer-readable medium having stored therein instructions executable by one or more processors to cause a device to perform the method of any of features 42-47.

[0252] (Feature 49) A device configured to perform the method of any of features 42-47.

[0253] (Feature 50) A media playback system configured to perform the method of any of features 42-47.

[0254] The specification is presented largely in terms of illustrative environments, systems, procedures, steps, logic blocks, processing, and other symbolic representations that directly or indirectly resemble the operations of data processing devices coupled to networks. These process descriptions and representations are typically used by those skilled in the art to most effectively convey the substance of their work to others skilled in the art. Numerous specific details are set forth to provide a thorough understanding of the present disclosure. However, it is understood to those skilled in the art that certain embodiments of the present disclosure can be practiced without certain, specific details. In other instances, well known methods, procedures, components, and circuitry have not been described in detail to avoid unnecessarily obscuring aspects of tiie embodiments.

Date reçue / Date received 2021-11-29