Method and apparatus for phonetic context adaptation for improved speech recognition

• US 20020087314A1
• Filed: 11/13/2001
• Published: 07/04/2002
• Est. Priority Date: 11/14/2000
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Fischer, Volker, Kunzmann, Siegfried, Tyrrell, A. Jon, Janke, Eric-W.
• Granted Patent: US 6,999,925 B2
• Time in Patent Office: Days
• US Class Current: 704/255
• CPC Class Codes: G10L 15/07 to the speaker

Abstract

The present invention provides a computerized method and apparatus for automatically generating from a first speech recognizer a second speech recognizer which can be adapted to a specific domain. The first speech recognizer can include a first acoustic model with a first decision network and corresponding first phonetic contexts. The first acoustic model can be used as a starting point for the adaptation process. A second acoustic model with a second decision network and corresponding second phonetic contexts for the second speech recognizer can be generated by re-estimating the first decision network and the corresponding first phonetic contexts based on domain-specific training data.

Claims

1. A computerized method of automatically generating from a first speech recognizer a second speech recognizer, said first speech recognizer comprising a first acoustic model with a first decision network and corresponding first phonetic contexts, and said second speech recognizer being adapted to a specific domain, said method comprising:

based on said first acoustic model, generating a second acoustic model with a second decision network and corresponding second phonetic contexts for said second speech recognizer by re-estimating said first decision network and said corresponding first phonetic contexts based on domain-specific training data.

2. The method of claim 1, wherein said domain-specific training data is of a limited amount only.

3. The method of claim 1, said re-estimating comprising:

partitioning said training data using said first decision network of said first speech recognizer.

4. The method of claim 3, said partitioning step comprising:

passing feature vectors of said training data through said first decision network and extracting and classifying phonetic contexts of said training data.

5. The method of claim 4, said re-estimating further comprising:

detecting domain-specific phonetic contexts by executing a split-and-merge methodology based on said partitioned training data for re-estimating said first decision network and said first phonetic contexts.

6. The method of claim 5, wherein control parameters of said split-and-merge methodology are chosen specific to said domain.

7. The method of claim 5, wherein for Hidden-Markov-Models (HMMs) associated with leaf nodes of said second decision network, said re-estimating comprises re-adjusting HMM parameters corresponding to said HMMs.

8. The method of claim 7, wherein said HMMs comprise a set of states s_i, and a set of probability-density-functions (PDFS) assembling output probabilities for an observation of a speech frame in said states s_i, and wherein said re-adjusting step is preceded by:

selecting from said states s_i a subset of states being distinctive of said domain; and

selecting from said set of PDFS a subset of PDFS being distinctive of said domain.

9. The method of claim 7, wherein said method is executed iteratively for additional training data.

10. The method of claim 8, wherein said method is executed iteratively for additional training data.

11. The method of claim 7, wherein said first and said second speech recognizer are general purpose speech recognizers.

12. The method of claim 7, wherein said first and said second speech recognizers are speaker-dependent speech recognizers and said training data is additional speaker-dependent training data.

13. The method of claim 7, wherein said first speech recognizer is a speech recognizer of at least a first language and said domain specific training data relates to a second language and said second speech recognizer is a multi-lingual speech recognizer of said second language and said at least first language.

14. The method of claim 1, wherein said domain is selected from the group consisting of a language, a set of languages, a dialect, a task area, and a set of task areas.

16. The machine-readable storage of claim 15, wherein said domain-specific training data is of a limited amount only.

17. The machine-readable storage of claim 15, said re-estimating comprising:

partitioning said training data using said first decision network of said first speech recognizer.

18. The machine-readable storage of claim 17, said partitioning step comprising:

passing feature vectors of said training data through said first decision network and extracting and classifying phonetic contexts of said training data.

19. The machine-readable storage of claim 18, said re-estimating further comprising:

detecting domain-specific phonetic contexts by executing a split-and-merge methodology based on said partitioned training data for re-estimating said first decision network and said first phonetic contexts.

20. The machine-readable storage of claim 19, wherein control parameters of said split-and-merge methodology are chosen specific to said domain.

21. The machine-readable storage of claim 19, wherein for Hidden-Markov-Models (HMMS) associated with leaf nodes of said second decision network, said re-estimating comprises re-adjusting HMM parameters corresponding to said HMMs.

22. The machine-readable storage of claim 21, wherein said HMMs comprise a set of states s_i and a set of probability-density-functions (PDFS) assembling output probabilities for an observation of a speech frame in said states s_i, and wherein said re-adjusting step is preceded by:

selecting from said states s_i a subset of states being distinctive of said domain; and

selecting from said set of PDFS a subset of PDFS being distinctive of said domain.

23. The machine-readable storage of claim 21, wherein said method is executed iteratively for additional training data.

24. The machine-readable storage of claim 22, wherein said method is executed iteratively for additional training data.

25. The machine-readable storage of claim 21, wherein said first and said second speech recognizer are general purpose speech recognizers.

26. The machine-readable storage of claim 21, wherein said first and said second speech recognizers are speaker-dependent speech recognizers and said training data is additional speaker-dependent training data.

27. The machine-readable storage of claim 21, wherein said first speech recognizer is a speech recognizer of at least a first language and said domain specific training data relates to a second language and said second speech recognizer is a multi-lingual speech recognizer of said second language and said at least first language.

28. The machine-readable storage of claim 15, wherein said domain is selected from the group consisting of a language, a set of languages, a dialect, a task area, and a set of task areas.

15. A machine-readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to automatically generate from a first speech recognizer a second speech recognizer, said first speech recognizer comprising a first acoustic model with a first decision network and corresponding first phonetic contexts, and said second speech recognizer being adapted to a specific domain, said machine-readable storage causing the machine to perform the steps of:

based on said first acoustic model, generating a second acoustic model with a second decision network and corresponding second phonetic contexts for said second speech recognizer by re-estimating said first decision network and said corresponding first phonetic contexts based on domain-specific training data.