Method for recognizing speech using eigenpronunciations

• US 20020128820A1
• Filed: 03/05/2002
• Published: 09/12/2002
• Est. Priority Date: 03/07/2001
• Status: Active Grant

• Current Assignee: Sony Deutschland GmbH (Sony Group Corp.)
• Original Assignee: Sony Deutschland GmbH (Sony Group Corp.)
• Inventors: Kompe, Ralf, Goronzy, Silke
• Granted Patent: US 7,113,908 B2
• Time in Patent Office: Days
• US Class Current: 704/10
• CPC Class Codes: G10L 15/07 to the speaker

Abstract

To increase the recognition rate and quality in a process of recognizing speech an approximative set of pronunciation rules (APR) for a current pronunciation (CP) of a current speaker is determined in a given pronunciation space (PS) and then applied to a current pronunciation lexicon (CL) so as to perform a speaker specific adaptation of said current lexicon (CL).

Claims

1. Method for recognizing speech,

wherein a pronunciation space (PS) of possible pronunciation rules and/or sets thereof is provided,

wherein in said pronunciation space (PS) an at least approximative set of pronunciation rules (APR) is determined and/or generated in accordance with a current pronunciation (CP) and/or accent of a current speaker, and

wherein at least one current lexicon (CL) or a dictionary of pronunciation variants which is employed for recognition is adapted to said current speaker by applying at least said approximative set of pronunciation rules (APR) to it, thereby at least including speaker specific pronunciation variants to said current lexicon (CL).

2. Method according to claim 1, wherein said step of adapting said current lexicon (CL) is carried out repeatedly, in particular after completed recognition steps and/or obtained recognition results.

3. Method according to claim 1 or 2, wherein said step of determining and/or generating said approximative set of pronunciation rules (APR) is carried out repeatedly, so as to iteratively find an approximative set of pronunciation rules (APR) fitting best to said current pronunciation (CP) and/or accent of said current speaker, in particular to consider temporal pronunciation and/or accent variations of said current speaker and/or in particular after completed recognition steps and/or obtained recognition results.

4. Method according to anyone of the preceding claims, wherein said pronunciation space (PS) is generated and/or provided in a pre-processing step, in particular in advance in a recognition process.

5. Method according to anyone of the preceding claims, wherein said pronunciation space (PS) is derived from a plurality and/or limited number of so-called Eigenpronunciations.

6. Method according to claim 5, wherein said Eigenpronunciations are derived from, contain and/or are representative for certain and given pronunciation rules and/or sets thereof, in particular for at least one non-native speaker of at least one target language (TL) with at least one source language (SL) as a mother or native tongue or language of said current speaker.

7. Method according to anyone of the preceding claims, wherein said pronunciation space (PS) is modified during the process of recognition, in particular after completed recognition steps and/or obtained recognition results and/or in particular by modifying said Eigenpronunciations.

8. Method according to anyone of the preceding claims, wherein said step of determining and/or generating said approximative set of pronunciation rules (APR) comprises a step of determining a pronunciation-related position of a current speaker in said pronunciation space (PS), in particular in accordance with a current pronunciation (CP) and/or accent of said current speaker.

9. Method according to anyone of the preceding claims, wherein said approximative set of pronunciation rules (APR) is chosen as a given and specific set of pronunciation rules in said pronunciation space (PS), in particular as a given and specific Eigenpronunciation thereof, which is a next neighbour of the speaker'"'"'s current pronunciation (CP), in particular with respect to said pronunciation-related position.

10. Method according to claim 9, wherein said property of being a next neighbour is evaluated by means of a certain given measure or distance function, in particular by an Euclidean distance, in said pronunciation space (PS).

11. Method according to anyone of the preceding claims, wherein said approximative set of pronunciation rules (APR) is chosen as a weighted mixture, superposition and/or the like of given pronunciation rules, sets, derivatives, and/or components thereof in said pronunciation space (PS), in particular of said Eigenpronunciations.

12. Method according to anyone of the preceding claims, wherein said current lexicon (CL) is in each case at least partially based on and/or derived from a starting lexicon (SL) or initial lexicon, in particular on a canonical lexicon essentially containing canonical pronunciation variants of native speakers of a given target language (TL) only and/or in particular in the case of changing to a different and/or new speaker.

13. Method according to anyone of the preceding claims, wherein the step of determining and/or generating said approximate set of pronunciation rules (APR) is at least partially based on and/or derived from a comparison of the current pronunciation (CP) with a canonical pronunciation, in particular with respect to a given utterance, recognition result and/or the like and/or in particular in the beginning of a recognition session with a different and/or new speaker.

14. Method according to claim 13, wherein said comparison is essentially based on a recognition step using said starting or canonical lexicon (SL) as said current lexicon (CL).

15. Method according to claim 13 or 14, wherein for said comparison at least one recognition step is repeated using a phone or phoneme recognizer, so as to yield a sequence of actually uttered phones, phonemes, or the like.

16. Method according to anyone of the claims 13 to 15, wherein for said comparison said current pronunciation (CP) of said current speaker is compared to a canonical pronunciation, in particular so as to generate an initial set of pronunciation rules (IR) and/or to locate the pronunciation-related position of said current speaker in said pronunciation space (PS).

17. Method according to anyone of the preceding claims, wherein from said current lexicon (CL) recognition related information, pronunciation variants and/or the like which are not covered by the speaking behaviour and/or by the current pronunciation of the current speaker are removed, so as to decrease the amount of data to be evaluated.

18. Method according to anyone of the preceding claims, which is designed for a plurality of source languages (SL) and/or of target languages (TL), in particular with respect to said Eigenpronunciations.

19. System for recognizing speech which is capable of performing the method according to anyone of the claims 1 to 18.

20. Computer program product, comprising computer program means adapted to perform and/or realize the method for recognizing speech according to anyone of the claims 1 to 18 and/or the steps thereof when it is executed on a computer, a digital signal pro-cessing means and/or the like.