Speech translation device

【0001】

[Technical field to which the invention belongs]

The present invention relates to a speech translation device that converts speech emitted by a user into another different language and outputs the converted speech.

【0002】

[Conventional technology]

Generally, a voice translation device recognizes a voice of a first language input from a microphone, translates the recognition signal into a second language, synthesizes the result, and outputs the result from a speaker. In the conventional technique, for example, as in Patent Document 1, there is a multilingual interpreting device that allows users of a plurality of different languages to speak at the same time using a large-scale computer and a communication medium.

【0003】

Further, a miniaturized and portable voice translator is disclosed in, for example, Patent Document 2, FIG. 5 is an external view of the small interpreter of Patent Document 1 from an oblique front, and FIG. 6 is a patent document. The external view of the small translator 1 from the diagonal rear surface is shown. In FIGS. 5 and 6, the housing 100 includes an information input / output unit 101 and a grip unit 102, and has a compact shape that can be operated with one hand. The information input / output unit 101 is equipped with a voice input means 103, a voice output means 104, and an information display means 105. When the power is turned on by the power switch 106 arranged on the rear surface of the small interpreter, the voice input switch 107 becomes operable, the voice input switch 107 is pressed, and the voice input means 103 performs voice input. Then, voice recognition of the input voice is performed, and the candidate character string is displayed on the information display means 105. The up movement switch 108 and the down movement switch 109 move the cursor in the information display means 105 up and down, select a candidate to be translated from the candidate character strings, and press the confirmation switch 110 to execute translation. Then, when the voice output switch 111 is pressed, voice is generated, and the voice is output through the voice output means 104. Here, the volume of the output voice is controlled by adjusting the volume control switch 112. If you want to cancel during these operations, press the cancel switch 113 to return to the state before voice input.

【0004】

[Patent Document 1]

Japanese Unexamined Patent Publication No. 2000-112939 [0005]

[Patent Document 2]

Japanese Unexamined Patent Publication No. 2000-315205 [0006]

[Problems to be Solved by the Invention]

However, in a device such as Patent Document 1, the user needs to carry a personal computer and a communication device when interpreting, and in the case of interpreting a simple conversation on an overseas trip, the system is easy to use. There wasn't.

【0007】

Further, the device of Patent Document 2 is miniaturized, and although it is possible to translate with one device, the structure becomes complicated. In terms of operability, there are many switches to be operated, such as voice input switch 107, voice output switch 111, confirmation switch 110, and cancel switch 113, and the translation is performed after the user inputs the voice of the first language. It takes time for the audio of the second language to be output. Furthermore, if you want to change the translation target, for example, to change from Japanese to English (Japanese-English) to Japanese to Chinese (Japanese-Chinese), a device that newly translates Japanese-Chinese It was necessary.

【0008】

The present invention has been made in view of the above circumstances so that persons who use different languages can easily communicate with each other and can easily cope with a plurality of different languages. It is an object of the present invention to provide a voice translation device.

【0009】

[Means for solving problems]

The above object of the present invention is that the microphone inputs the voice of the first language, the voice recognition means recognizes the voice of the first language as the voice signal of the first language, and the translation means receives the voice signal of the first language. A voice translation device that converts into a voice signal of a second language, the voice generation means generates the voice of the second language from the voice signal of the second language, and the speaker outputs the voice of the second language. The voice translation device has a main body unit and a data unit including a storage medium that stores voice-translation data for each language to be translated, and includes a mounting portion that allows the data unit to be detachably attached to the case of the main body unit. And, it is achieved by exchanging the data unit according to the language to be translated.

【0010】

Further, for the above purpose, the voice recording means records the voice input through the microphone, the memory arranged in the main body unit stores the recorded voice, and the speaker stores the stored voice. It is effectively achieved by outputting.

【0011】

Further, the above purpose is to provide a rod-shaped grip portion in which the case of the main body unit has a switch for starting voice input and can operate the switch while holding the switch with one hand, and the microphone. This is effectively achieved by having the speaker and a main body portion formed in a shape in which the front surface and the rear surface can be clearly seen.

【0012】

Further, for the above purpose, the mounting portion for making the data unit removable in the case of the main body unit is provided in a recess provided on the bottom surface of the grip portion and in the upper portion of the data unit to be fitted into the recess. It is effectively achieved by being composed of the arranged convex portions.

【0013】

Further, the above purpose is to include one microphone and one speaker on the front surface and the rear surface of the main body, and when the sound of the first language is input to the microphone on the front surface, the second language is used. When the sound converted to is output from the speaker on the rear surface and the sound of the second language is input to the microphone on the rear surface, the sound converted to the first language is output from the speaker on the front surface. By being, it is effectively achieved.

【0014】

BEST MODE FOR CARRYING OUT THE INVENTION

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

【0015】

FIG. 1 is a diagram showing a configuration of a speech translation device showing an embodiment of the present invention. In the figure, the voice translation device 1 includes a CPU 2, a memory 3, a peripheral control device 4, a voice input device 5, a voice output device 6, switches 7, 8, voice recording means 9, and a main unit 11 including a recording switch 10. It is composed of a data unit 12 including recognition data 12a and translation data 12b.

【0016】

The audio input means 5 includes a microphone 13 and an A / D converter 14, and the audio output means includes a speaker 15 and a D / A converter 16, one each on the front side and the rear side. The voice of the first language input from the voice input means 5 on the front side is translated into the second language and output from the voice output means 6 on the rear side, and is also input from the voice input means 5 on the rear side. The audio in two languages is translated into the first language and output from the audio output means 6 on the front side.

【0017】

In CPU2, the voice recognition means 2a that recognizes the voice of the first language as the voice signal of the first language, or recognizes the voice of the second language as the voice signal of the second language, and the voice signal of the first language is the second. Translation means 2b for converting a language signal or converting a second language voice signal into a first language voice signal, generating a second language voice from a second language voice signal, or a first language Functions such as voice generation means 2c that generates the voice of the first language from the voice signal of the above are executed.

【0018】

The data unit 12 stores programs and various data executed by the CPU 2 for each translation target language. Here, the various data are recognition data 12a, which is a reference for speech recognition, and translation data 12b, which is a reference for translation. Also, since the data unit 12 is detachably attached to the mounting part 17, by removing the data unit 12 and attaching another data unit with a different translation target language, for example, Japanese-English translation was possible. Things can be converted into Japanese-Chinese translations.

【0019】

The memory 3 is mainly used as a work area for arithmetic processing performed by the CPU 2. In addition, programs and various data stored in the data unit 12 may be loaded.

【0020】

Although not particularly limited, the switch 7 is a switch that starts the voice input means 5 on the front side, and the switch 8 is a switch that starts the voice input means 5 on the rear side.

【0021】

In addition, the voice translation device 1 is equipped with a voice recording means 9, and the recording switch 10 can start recording and store the voice recorded from the microphone 13 in the memory 3. The stored voice can also be played back from the speaker 15.

【0022】

Subsequently, the operation and operation of this device will be described.

【0023】

When the switch 7 on the front side is pressed, the first language sound captured through the microphone 13 on the front side is converted into a digital signal by the A / D converter 14 and then captured by the peripheral control device 4. The voice signal of the first language is recognized by the voice recognition means 2a in the CPU 2, and the recognition data 12a stored in the data unit 12 is referred to here. The recognized first language audio signal is translated into a second language audio signal by the translation means 12b in the CPU 2, and here, the translation data 12b stored in the data unit 12 is referred to. The translated second language voice signal is generated into the second language voice by the voice generation means 2c in the CPU 2 and sent to the peripheral control device 4. The arithmetic processing in these CPU 2s is performed while using the memory 3 as a work area. The generated second language voice is transmitted from the peripheral controller 4 to the D / A converter 16 where it is converted into an analog signal. The second language voice converted to analog is output through the speaker 15 on the rear side.

【0024】

Also, even if the switch 8 on the rear side is pressed and the second language is taken in through the microphone 13 on the rear side, the same operation as described above is performed, and the translated voice of the first language is the speaker on the rear side. Output via 15.

【0025】

FIG. 2 shows an external view of the speech translation device according to an embodiment of the present invention from an oblique front surface, and FIG. 3 shows an external view of the speech translation apparatus according to an embodiment of the present invention from an oblique rear surface. In FIGS. 3 and 4, the case 21 of the voice translation device 1 has a main body 20a including an audio unit 21 having a microphone 13 and a speaker 15, switches 7, 8, a recording switch 9, and a data unit removal switch. It is composed of a grip portion 21b having 23. The main body portion 21a is formed in a thick plate shape in which the front surface and the rear surface can be clearly seen, and the grip portion 21b is formed in a rod shape in which the above-mentioned buttons can be operated while being held with one hand.

【0026】

The audio unit 22 is provided on both the front surface and the rear surface. As described above, when the switch 7 is pressed and the voice of the first language (here, Japanese) is input from the front surface, the second language translated from the rear surface is performed. The voice of the language (English in this case) is output, and when the switch 8 is pressed and the voice of the second language (English) is input from the rear, the translated voice of the first language (Japanese) is output.

【0027】

FIG. 4 is an external view showing a state in which the data unit of the speech translation apparatus according to the first embodiment of the present invention is separated from the oblique rear surface. In the figure, the data unit 12 is removable by the data unit removal switch 23, and the mounting portion 17 has a connection portion recess 17a provided on the bottom surface of the grip portion 21b and a protrusion provided on the upper surface of the data unit 12. It consists of part 17b. The mounting structure is such that a groove is provided on a part of the side surface of the convex portion 17b, and a claw provided in the concave portion 17a is caught in the groove to fix the data unit 12. Further, when the data unit removal button 23 is pressed, the claw is removed from the groove, and the data unit 12 can be removed. This removal structure is not particularly limited, and for example, a structure for inserting into an outlet type, a structure in which a convex portion is provided on the bottom surface of the grip portion 20b, and a structure in which a convex portion is provided on the upper surface of the data unit 12 is inserted and attached. You may. As mentioned above, by removing the data unit 12 for Japanese-English translation and attaching the data unit 12'for Japanese-Chinese translation, from Japanese-English translation to Japanese-Chinese translation Can be converted to.

【0028】

Although the present invention has been specifically described above, the present invention is not limited thereto, and various modifications can be made without departing from the spirit of the present invention.

【0029】

[Effect of the invention]

As described above, according to the present invention, the voice input through the microphone is recognized as the voice signal of the first language, and the voice signal of the first language is converted into the voice signal of the second language according to a predetermined rule. In a voice translation device that emits voice to the outside through a speaker, it is possible to translate between different languages by exchanging the unit including a storage medium that stores voice-translation data for each translation target according to the translation target. I made it. As a result, it is not necessary to purchase a device for each translation target, and the work of attaching and detaching is easy, so that it is possible to respond flexibly to multiple languages.

【0030】

In addition, by making the case of the device small and easy to operate while holding it with one hand, it can be easily taken on a trip, etc., and it remains in a natural posture during dialogue without feeling the language barrier. I can communicate.

【0031】

In addition, the first language voice input means and the second language voice output means are provided on the front side, and the first language voice output means and the second language voice input means are provided on the back side. As a result, both can be translated while one person holds the device, so that the dialogue can be efficiently promoted.

[Simple explanation of drawings]

FIG. 1 is a configuration diagram of a speech translation device showing an embodiment of the present invention.

FIG. 2 is an external view of a speech translation device showing an embodiment of the present invention from an oblique front view.

FIG. 3 is an external view of a speech translation device showing an embodiment of the present invention from an oblique rear surface.

FIG. 4 is an external view showing a state in which a data unit of a speech translation device according to an embodiment of the present invention is removed from an oblique rear surface.

FIG. 5 is an external view from an oblique front view showing a conventional small interpreter.

FIG. 6 is an external view from an oblique rear surface showing a conventional small translator.

[Explanation of symbols]

1 Voice translator 2 CPU2a Voice recognition means 2b Translation means 2c Voice generation means 3 Memory 9 Voice recording means 11 Main unit 12 Data unit 13 Microphone 15 Speaker 17 Mounting 17a Concave 17b Convex 21 Case 21a Main body 21b Grip