Method for modifying speech speed
Abstract
The modification method has an analogue speech signal converted into a corresponding digital signal. The digital signal is entered in a memory, with lengthening or shortening of the signal by a pre-defined factor, using an add overlap method. The stored speech signal is divided into segments which are weighted via a window function with a first rising section, a constant section and a falling section. There is a comparison made of the weighted segments, for waveform similarity and addition of the segments, when the similarity has a maximum value.

Term
Term ended
Projected expiry passed 12 March 2018, 8.5 years ago.
- Priority
- Filed
- Published
- Projected expiry
- Today
2 claims: 2 independent, 0 dependent
- 1Method for speed modification of speech signals, in particular digitized speech signals, in whichan analog speech signal is digitized, resulting in a digitized speech signal which is stored in a memory,a factor α is defined by which the speech signal is lengthened or shortened,- A window function is defined with a first rising section of length N, a second, constant section of length L directly adjoining the first section and a third falling section directly adjoining the second section, with a superposition of the first rising section of a window with the third falling section of another window and an addition of both sections in the overlap area, the result is one, which corresponds to the value of the second section of the window function,segments of a length L + N are taken from the digitized, stored speech signal at irregular intervals of an average length αL,- These segments, taken from the digitized, stored speech signal, are weighted with the window function in the time domainthe weighted segments are each added up offset by a defined number of L samples, as a result of which the resulting speech signal is extended by the factor α or shortened by 1 / α,characterized,that, at the points at which the segments are extracted from the digitized speech signal, the segment extracted there, weighted with the window function, is compared with the segment subsequently extracted, also weighted with the window function, under similarity aspects,that for a quick comparison of the similarity of the segments, only the third section of the segment, weighted with the falling window section, is compared with the first section of the following segment, weighted with the increasing N section window section,- That these segments are added to each other offset when the similarity of the two compared segments is maximum and- That a correlation is used to calculate the similarity, as its measure. Verfahren zur Geschwindigkeitsmodifikation von Sprachsignalen, insbesondere digitalisierten Sprachsignalen, bei dem - ein analoges Sprachsignal digitalisiert wird, wodurch ein digitalisiertes Sprachsignal entsteht, welches in einem Speicher gespeichert wird,- ein Faktor α definiert wird, um welchen das Sprachsignal verlängert oder verkürzt wird,- eine Fensterfunktion mit einem ersten steigenden Abschnitt der Länge N, einem zweiten, sich direkt an den ersten Abschnitt anschließenden, konstanten Abschnitt der Länge L und einem dritten, sich direkt an den zweiten Abschnitt anschließenden, fallenden Abschnitt definiert wird, wobei bei einer Überlagerung des ersten steigenden Abschnittes eines Fensters mit dem dritten fallenden Abschnitt eines anderen Fensters und einer Addition beider Abschnitte im Überlappungsbereich, sich das Ergebnis eins ergibt, was dem Wert des zweiten Abschnittes der Fensterfunktion entspricht,- aus dem digitalisierten, gespeicherten Sprachsignal in unregelmäßigen Abständen einer mittleren Länge αL Segmente einer Länge L+N entnommen werden,- diese, aus dem digitalisierten, gespeicherten Sprachsignal entnommenen, Segmente mit der Fensterfunktion im Zeitbereich gewichtet werden- die gewichteten Segmente jeweils um eine definierte Anzahl von L Abtastwerten versetzt aufaddiert werden, wodurch das so entstehende Sprachsignal um den Faktor α verlängert bzw. um 1/α verkürzt wird, dadurch gekennzeichnet,- daß nacheinander an den Stellen der Entnahme der Segmente aus dem digitalisierten Sprachsignal, das dort entnommene, mit der Fensterfunktion gewichtete, Segment mit dem nachfolgend entnommenen, ebenfalls mit der Fensterfunktion gewichteten, Segment unter Ähnlichkeitsaspekten verglichen wird,- daß zum schnellen Vergleich der Ähnlichkeit der Segmente lediglich der N Werte lange dritte, mit dem fallenden Fensterabschnitt gewichtete, Abschnitt des Segmentes mit dem jeweils ersten, mit dem steigenden N Werte langen Fensterabschnitt gewichteten Abschnitten des nachfolgenden Segmentes verglichen wird,- daß diese Segmente zueinander versetzt aufaddiert werden, wenn die Ähnlichkeit beider verglichener Segmentteile maximal ist und- daß zur Berechnung der Ähnlichkeit, als deren Maß, eine Korrelation verwendet wird.
- 2Method for speed modification of speech signals, in particular digitized speech signals, in whichan analog speech signal is digitized, resulting in a digitized speech signal which is stored in a memory,a factor α is defined by which the speech signal is lengthened or shortened,- A window function is defined with a first rising section of length N, a second, constant section of length L directly adjoining the first section and a third falling section directly adjoining the second section, with a superposition of the first rising section of a window with the third falling section of another window and an addition of both sections in the overlap area, the result is one, which corresponds to the value of the second section of the window function,segments of a length L + N are taken from the digitized, stored speech signal at irregular intervals of an average length αL,these segments, taken from the digitized, stored speech signal, are weighted with the window function in the time domain,the weighted segments are each added up offset by a defined number of L samples, as a result of which the resulting speech signal is extended by the factor α or shortened by 1 / α,characterized,that, at the points where the segments are removed from the digitized speech signal, the segment extracted there is compared with the result of the synthesis with the segment subsequently extracted,that for the quick comparison of the deviation of the respective synthesis result from the original signal, only the N section, long third section of the last segment taken, is used as a reference,- That these segments are added to each other offset when the determined deviation is minimal and- That the relative error or the absolute quadratic error is used as a measure of the deviation. Verfahren zur Geschwindigkeitsmodifikation von Sprachsignalen, insbesondere digitalisierten Sprachsignalen, bei dem - ein analoges Sprachsignal digitalisiert wird, wodurch ein digitalisiertes Sprachsignal entsteht, welches in einem Speicher gespeichert wird,- ein Faktor α definiert wird, um welchen das Sprachsignal verlängert oder verkürzt wird,- eine Fensterfunktion mit einem ersten steigenden Abschnitt der Länge N, einem zweiten, sich direkt an den ersten Abschnitt anschließenden, konstanten Abschnitt der Länge L und einem dritten, sich direkt an den zweiten Abschnitt anschließenden, fallenden Abschnitt definiert wird, wobei bei einer Überlagerung des ersten steigenden Abschnittes eines Fensters mit dem dritten fallenden Abschnitt eines anderen Fensters und einer Addition beider Abschnitte im Überlappungsbereich, sich das Ergebnis eins ergibt, was dem Wert des zweiten Abschnittes der Fensterfunktion entspricht,- aus dem digitalisierten, gespeicherten Sprachsignal in unregelmäßigen Abständen einer mittleren Länge αL Segmente einer Länge L+N entnommen werden,- diese, aus dem digitalisierten, gespeicherten Sprachsignal entnommenen, Segmente mit der Fensterfunktion im Zeitbereich gewichtet werden,- die gewichteten Segmente jeweils um eine definierte Anzahl von L Abtastwerten versetzt aufaddiert werden, wodurch das so entstehende Sprachsignal um den Faktor α verlängert bzw. um 1/α verkürzt wird, dadurch gekennzeichnet,- daß nacheinander an den Stellen der Entnahme der Segmente aus dem digitalisierten Sprachsignal, das dort entnommene Segment mit dem Resultat der Synthese mit dem nachfolgend entnommenen Segment verglichen wird,- daß zum schnellen Vergleich der Abweichung des jeweiligen Syntheseresultats vom Originalsignal lediglich der N Werte lange dritte Abschnitt des zuletzt entnommenen Segmentes als Referenz herangezogen wird,- daß diese Segmente zueinander versetzt aufaddiert werden, wenn die ermittelte Abweichung minimal ist und- daß als Maß für die Abweichung der relative Fehler oder der absolute quadratische Fehler herangezogen wird.
Independent claims2
21 paragraphs, as filed
The invention relates to a method for speed modification of speech signals in the time domain, in particular an efficient overlap add method.
In various areas of the processing of speech and audio signals, a change in the playback speed of these signals is desired, if possible without impairing their naturalness and - in the case of speech - their intelligibility. This goal of maintaining the sound character can be formulated from a technical point of view as follows: Despite a modification of the time scale of these signals, their short-term spectral properties should remain unchanged. For voice signals in particular, this means that the fundamental frequency and formants must be retained when modifying the speed.
The time compression or expansion of audio signals is used in studios, for example with the aim of trimming advertising programs to the intended length. In dictation technology, too, it is important to adapt the playback speed to the needs and skills of the typist. Another application is in the real-time transmission of voice signals, in which data packets arrive at the receiver with a variable delay. By using the speed modification, the overall delay can be kept lower on average than the worst-case delay of the transmission link, without a data packet arriving too late leading to dropouts or other, similarly disturbing effects. For many applications, in addition to the desire for the highest possible sound quality, the following additional requirements apply to the process:
Inexpensive real-time implementation must be achievable, and it must be possible to change the speed modification factor as continuously as possible at runtime. It is undoubtedly also advantageous if the algorithm does not have a pitch estimate that is always faulty.
From "Method for Time or Frequency Compression-Expansion of Speed", by G. Fairbaks and RP Jaeger, Inst. Of Radio Engineers Trans. On Audio, Vol. AU-2, No. 1 pp. 7-12, Jan. 1954, the first examinations of speech signal compression or speech signal expansion are known. Since then, frequency domain methods have been used frequently - as is obvious since, as mentioned at the beginning, the short-term spectral properties of the speech signal are to be retained. Since the mid-eighties, comparatively simple overlap-add methods operating in the time domain have been known, with which very good-sounding time-scaled speech signals can be generated.
In "Signal Estimation from Modified Short-Time Fourier Transform", by DW Griffin, in IEEE Trans. Acoust., Speech, Signal Processing, Vol. ASSP-32, No. 2, pp. 236-242, Apr. 1984, Griffin and Lim report experiments with a very complex iterative phase determination. The publication of S. Roucos and AM Wilgus "High Quality Time-Scale Modification for Speech", IEEE Proc, takes this approach in turn. Int. Conf. Acoust., Speech, Signal Processing, pp. 493-496, 1985, reference that propose a time domain method that generates time-scaled speech signals using an overlap add approach. In this so-called SOLA method (SOLA = Synchronized OverLap-Add), the sections taken at regular intervals from the original signal are synchronized by shifting before the corresponding windowing and addition in the target signal. In the broader sense, this corresponds to phase optimization as it is carried out in the frequency domain method. The so-called WSOLA method (WSOLA = Waveform Similarity OverLap - Add) is closely related to the SOLA algorithm, which W. Verhelst and M. Roelands in "An Overlap-Add Technique Based on Waveform Similarity (WSOLA) for High Quality Time -Scale Modification of Speed ", IEEE Proc. Int. Conf. Acoust., Speech, Signal Processing, pp. 554-557, 1993, and "Waveform Similarity Based Overlap-Add (WSOLA) for Time-Scale Modification of Speech: Structures and Evaluation", Int. Conf. on Speech Communication and Technology, pp. 337-340, 1993. The main difference between these two approaches lies in the synchronization, which is carried out in the WSOLA process by staggered removal of segments from the original signal, which has a major impact on the SOLA principle. 7 The object of the invention is to provide a method for speed modification of speech signals in the time domain, which works particularly efficiently and requires less effort compared to the prior art.
This object is solved by the features of claims 1 and 2. Advantageous embodiments of the invention are given in the following description.
The version y (k) of a speech signal x (k) time-scaled by the factor α is generated according to the synthesis<maths id="math0001" num=""><math display="block"><mrow><mtext mathvariant="italic">y</mtext><mtext>(</mtext><mtext mathvariant="italic">k</mtext><mtext>)= </mtext><apply><sum /><lowlimit><mtext>λ = -∞</mtext></lowlimit><uplimit><mtext>∞</mtext></uplimit><mrow><mtext>(</mtext><mtext mathvariant="italic">k</mtext><mtext>+ Λ (α-1)</mtext><mtext mathvariant="italic">L</mtext><msub><mrow><mtext>+ Δ</mtext></mrow><mrow><mtext>λ</mtext></mrow></msub><mtext>)</mtext><mtext mathvariant="italic">w</mtext><mtext>(</mtext><mtext mathvariant="italic">k</mtext><mtext>-λ</mtext><mtext mathvariant="italic">L</mtext><mtext>)</mtext></mrow></apply></mrow></math><img file="EP0865026A2_D0001.tif" /></maths> with a window function<maths id="math0002" num=""><img file="EP0865026A2_D0002.tif" /></maths>
The function v (k) defined here for k = 0, ..., N-1 makes sense between its extremes <maths id="math0003" num=""><math display="inline"><mrow><msub><mrow><mtext>v (0) = ε</mtext></mrow><mrow><mtext>0</mtext></mrow></msub></mrow></math><img file="EP0865026A2_D0003.tif" /></maths> with 0 <ε<sub>0</sub><< 1 and <maths id="math0004" num=""><math display="inline"><mrow><msub><mrow><mtext>v (N-1) = 1-ε</mtext></mrow><mrow><mtext>1</mtext></mrow></msub></mrow></math><img file="EP0865026A2_D0004.tif" /></maths> with 0 <ε<sub>1</sub><< 1 growing monotonously.
The specified w (k) definition ensures that the condition necessary for meaningful overlap add<maths id="math0005" num=""><math display="block"><mrow><apply><sum /><lowlimit><mtext>λ = -∞</mtext></lowlimit><uplimit><mtext>∞</mtext></uplimit><mrow><mtext mathvariant="italic">w</mtext><mtext>(</mtext><mtext mathvariant="italic">k</mtext><mtext>-</mtext><mtext mathvariant="italic">λL</mtext><mtext>) ≡ 1 ∀</mtext><mtext mathvariant="italic">k</mtext><mtext> ε {-∞, ..., ∞}</mtext></mrow></apply></mrow></math><img file="EP0865026A2_D0005.tif" /></maths> is satisfied.
The shift variable Δ contained in the above synthesis equation<sub>λ</sub> is out of a "tolerance range" -Δ for the purpose of the mentioned synchronization<sub>Max</sub>, ..., Δ<sub>Max</sub> to determine.
The basic procedure is as follows: Apart from a synchronization-related “jitter”, segments of length L + N are taken from the original signal x (apart from a synchronization-related “jitter”) and, after weighting with w (k), are added by L sample values each offset. The signal y (k) obtained in this way is accelerated by a factor of α compared to x (k), that is to say that an utterance of K samples in the original signal x (k) length on this y (k) section by this procedure the length K / α is mapped, that is to say shortened and thus accelerated in the reproduction for α> 1, or lengthened, that is to say slowed down, if α <1.
The synchronization of the sections to be overlapped is of great importance for the resulting sound quality. The following approach is used for this purpose: While the method is being processed, the segment of x (k) offset by L samples can be regarded as the "ideal segment" for the next step for each segment extracted from the signal x (k), since this selection means that Overlap add operation would reproduce the original signal x (k) again. However, the desired time scaling now requires that a different section of x (k) which is offset from the "ideal segment" is generally selected for the overlap-add synthesis. The best possible synchronization is given when the section used for the overlap add operation has the greatest possible similarity ("waveform similarity") with the "ideal segment".
As a criterion for the similarity of the segments mentioned, there are various dimensions. For example, the use of the correlation coefficient is obvious. While W. Verhelst and M. Roelands in "An Overlap-Add Technique Based on Waveform Similarity (WSOLA) for High Quality Time-Scale Modification of Speed", in IEEE Proc. Int. Conf. Acoust., Speech, Signal Processing, pp. 554-557, 1993, and "Waveform Similarity Based Overlap-Add (WSOLA) for Time-Scale Modification of Speech: Structures and Evaluation" in Int. Conf. on Speech Communication and Technology, pp. 337-340, 1993, for the evaluation of the similarity measure using the complete segment of length L + N, it appears to be perfectly sufficient to limit the calculation to the range of the N samples in which the segments actually overlap.
For the further representations it is helpful to introduce the following vector notation: The N-value section of the "ideal segment" in which the overlap with the segment to be newly determined will take place is denoted by x, and the first N values of the shifted segment by x<sub>q</sub>, The weighting of this section with the rising edge of the window is represented by multiplying this vector by a diagonal matrix V, which is populated with the values v (0), ..., v (N-1). Accordingly, the weighting of the ideal segment section x is multiplied by the falling edge of the window<b>1</b> - V shown, where <b>1</b> denotes the N × N unit matrix. The y (k) section resulting from the overlap-add synthesis in the critical overlap region is thus<maths id="math0006" num=""><img file="EP0865026A2_D0006.tif" /></maths>
For example, a cross-correlation calculation can now be used as a measure of the similarity of the components involved<maths id="math0007" num=""><img file="EP0865026A2_D0007.tif" /></maths> specify. Maximizing this expression in terms of the in x<sub>q</sub> recovering shift δ ∈ {-Δ<sub>Max</sub>, ..., Δ<sub>Max</sub>} provides the optimal shift Δ for the segment under consideration in terms of the similarity measure used<sub>λ</sub>.
The calculation of the C<sub>δ</sub> Requires 2N multiplications every L samples to precalculate expression x<sup>T</sup>(<b>1</b>-V)<sup>T</sup>V and then (2Δ<sub>Max</sub>+1) N multiplications and additions.
This contrasts with W. Verhelst and M. Roelands in "An Overlap-Add Technique Based on Waveform Similarity (WSOLA) for High Quality Time-Scale Modification of Speed", in IEEE Proc. Int. Conf. Acoust., Speech, Signal Processing, pp. 554-557, 1993, and "Waveform Similarity Based Overlap-Add (WSOLA) for Time-Scale Modification of Speech: Structures and Evaluation" in Int. Conf. on Speech Communication and Technology, pp. 337-340, 1993, represents a reduction in effort by a factor of two, which even increases for L> N. Limiting the similarity calculation to the area of overlap has no negative effects on the quality of the time-scaled speech samples.
Another approach to synchronization is to minimize the error between the synthesized signal y and the original signal x instead of maximizing the "waveform similarity". A simple arbitrary choice is to use the quadratic expression for this error<maths id="math0008" num=""><math display="block"><mrow><msub><mrow><mtext>e</mtext></mrow><mrow><mtext>δ</mtext></mrow></msub><msup><mrow><mtext> = ∥xy∥</mtext></mrow><mrow><mtext>2</mtext></mrow></msup></mrow></math><img file="EP0865026A2_D0008.tif" /></maths> to be set.
If the precalculations are neglected, this amounts to the evaluation of E<sub>δ</sub> effort to (2Δ<sub>Max</sub>+1) 4N DSP operations every L samples. These are operations that a signal processor with common architecture can process in one step.
Another approach is to use the relative error instead of the absolute error<maths id="math0009" num=""><math display="block"><mrow><mtext>R∂ = </mtext><mfrac><mrow><mtext>∥</mtext><mtext mathvariant="italic">x</mtext><mtext> - </mtext><mtext mathvariant="italic">y</mtext><msup><mrow><mtext>∥</mtext></mrow><mrow><mtext>2</mtext></mrow></msup></mrow><mrow><mtext>∥</mtext><mtext mathvariant="italic">y</mtext><msup><mrow><mtext>∥</mtext></mrow><mrow><mtext>2</mtext></mrow></msup></mrow></mfrac></mrow></math><img file="EP0865026A2_D0009.tif" /></maths> to minimize what can be interpreted as SNR maximization. (2Δ<sub>Max</sub>+1) 5N operations are required here before each overlap add operation.
9 sheets
Sheet 1 Sheet 2 Sheet 3 Sheet 4 Sheet 5 Sheet 6 Sheet 7 Sheet 8 Sheet 9
Every citation, both ways
| Document | Relation | Office | Cited during |
|---|---|---|---|
| WO2006048349A1 | Cited by | World Intellectual Property Organization (WIPO) | International search |
| US7610205B2 | Cited by | United States of America | Applicant |
| WO2004114282A1 | Cited by | World Intellectual Property Organization (WIPO) | International search |
| US8270366B2 | Cited by | United States of America | Applicant |
| US6944510B1 | Cited by | United States of America | Applicant |
| US7711123B2 | Cited by | United States of America | Applicant |
| US7461002B2 | Cited by | United States of America | Applicant |
| US8195472B2 | Cited by | United States of America | Applicant |
| US7283954B2 | Cited by | United States of America | Applicant |
| US7894654B2 | Cited by | United States of America | Applicant |
| US7461002B2 | Cited by | United States of America | Applicant |
| US7313519B2 | Cited by | United States of America | Applicant |
| CN102855884A | Cited by | China | Search report |
| US8488800B2 | Cited by | United States of America | Applicant |
| US7610205B2 | Cited by | United States of America | Applicant |
| EP0427953A2 | Cites | European Patent Office (EPO) | Search report |
| EP0608833A2 | Cites | European Patent Office (EPO) | Search report |
| EP0726560A2 | Cites | European Patent Office (EPO) | Search report |
7 members in 3 offices
Priority claims5
| Document | Office | Kind | Date |
|---|---|---|---|
| 19710545 | Germany | A | |
| 19710545 | Germany | A | |
| 19710545 | Germany | – | |
| 19710545 | – | – | – |
| DE1997110545 | – | – | – |
Members7
| Document | Office | Kind | |
|---|---|---|---|
| DE19710545C1 | Germany | C1 | |
| EP0865026A2This record | European Patent Office (EPO) | A2 | |
| EP0865026A3 | European Patent Office (EPO) | A3 | |
| EP0865026B1 | European Patent Office (EPO) | B1 | |
| AT255763T | Austria | T | |
| ATE255763T1 | Austria | T1 | |
| DE59810302D1 | Germany | D1 |
44 legal events, as 5 offices reported them to INPADOC
Over the term
Point at a mark for the eventEvents
| Event | Code | Office | |
|---|---|---|---|
| Lapsed in a contracting state [announced via postgrant information from national office to epo]LapsedPG25 | PG25 | EP | |
| Lapsed in a contracting state [announced via postgrant information from national office to epo]LapsedPG25 | PG25 | EP | |
| Lapsed in a contracting state [announced via postgrant information from national office to epo]LapsedPG25 | PG25 | EP | |
| Notification of lapseLapsedST | ST | FR | |
| Gb: european patent ceased through non-payment of renewal feeCeasedGBPC | GBPC | EP | |
| Application deemed withdrawn, or ip right lapsed, due to non-payment of renewal feeWithdrawnR119 | R119 | DE | |
| Annual fee paid to national office [announced via postgrant information from national office to epo]GrantedPGFP | PGFP | EP | |
| Annual fee paid to national office [announced via postgrant information from national office to epo]GrantedPGFP | PGFP | EP | |
| Annual fee paid to national office [announced via postgrant information from national office to epo]GrantedPGFP | PGFP | EP | |
| Change of representativeR082 | R082 | DE | |
| Fee paymentPLFP | PLFP | FR | |
| Lapsed in a contracting state [announced via postgrant information from national office to epo]LapsedPG25 | PG25 | EP | |
| Lapsed in a contracting state [announced via postgrant information from national office to epo]LapsedPG25 | PG25 | EP | |
| Lapsed because of non-payment of the annual feeLapsedV1 | V1 | NL | |
| Annual fee paid to national office [announced via postgrant information from national office to epo]GrantedPGFP | PGFP | EP | |
| Annual fee paid to national office [announced via postgrant information from national office to epo]GrantedPGFP | PGFP | EP | |
| Nl: assignments of ep-patentsNLS | NLS | EP | |
| Transmission of propertyTP | TP | FR | |
| Amendments to the register in respect of changes of name or changes affecting rights (sect. 32/1977)732E | 732E | GB | |
| No opposition filedOpposition26N | 26N | EP | |
| No opposition filed within time limitOppositionORIGINAL CODE: 0009261PLBE | PLBE | EP | |
| Information on the status of an ep patent application or granted ep patentGrantedSTATUS: NO OPPOSITION FILED WITHIN TIME LIMITSTAA | STAA | EP | |
| Fr: translation filedET | ET | EP | |
| Corresponds to:REF | REF | EP | |
| Gb: translation of ep patent filed (gb section 77(6)(a)/1977)GBT | GBT | EP | |
| Designated contracting statesAK | AK | EP | |
| European patent grantedGrantedNOT ENGLISHFG4D | FG4D | GB | |
| (expected) grantORIGINAL CODE: 0009210GRAA | GRAA | EP | |
| Grant fee paidORIGINAL CODE: EPIDOSNIGR3GRAS | GRAS | EP | |
| Information provided on ipc code assigned before grantRIC1 | RIC1 | EP | |
| Information provided on ipc code assigned before grantRIC1 | RIC1 | EP | |
| Title (correction)METHOD FOR MODIFYING SPEECH SPEEDRTI1 | RTI1 | EP | |
| Despatch of communication of intention to grant a patentORIGINAL CODE: EPIDOS IGRAGRAH | GRAH | EP | |
| First examination report despatched17Q | 17Q | EP | |
| Information provided on ipc code assigned before grant7G 10L 21/04 ARIC1 | RIC1 | EP | |
| Party data changed (applicant data changed or rights of an application transferred)RAP1 | RAP1 | EP | |
| Designation fees paidAT DE FR GB NLAKX | AKX | EP | |
| Request for examination filed17P | 17P | EP | |
| Designated contracting statesAK | AK | EP | |
| Request for extension of the european patentAL;LT;LV;MK;RO;SIAX | AX | EP | |
| Search report despatchedORIGINAL CODE: 0009013PUAL | PUAL | EP | |
| Designated contracting statesAK | AK | EP | |
| Request for extension of the european patentAL;LT;LV;MK;RO;SIAX | AX | EP | |
| Public reference made under article 153(3) epc to a published international application that has entered the european phaseORIGINAL CODE: 0009012PUAI | PUAI | EP |
Numbers
- Publication
- 0865026
- Publication, DOCDB
- 0865026
- Publication, EPODOC
- EP0865026
- Application
- 98104455
- Application, DOCDB
- 98104455
- Application, EPODOC
- EP19980104455
Titles3
- German
- Effizientes Verfahren zur Geschwindigkeitsmodifikation von Sprachsignalen
- English
- Method for modifying speech speed
- French
- Méthode pour la modification du débit de parole
Classification
- CPC, 1
- G10L21/04
- IPC, 1
- G10L21 04
Designated states24
- Contracting states, 18
- Austria
- Belgium
- Switzerland
- Germany
- Denmark
- Spain
- Finland
- France
- United Kingdom
- Greece
- Ireland
- Italy
- Liechtenstein
- Luxembourg
- Monaco
- Netherlands (Kingdom of the)
- Portugal
- Sweden
- Extension states, 6
- Albania
- Lithuania
- Latvia
- North Macedonia
- Romania
- Slovenia