POSITION-DEPENDENT PHONETIC MODELS FOR RELIABLE PRONUNCIATION IDENTIFICATION

• US 20120191456A1
• Filed: 02/01/2012
• Published: 07/26/2012
• Est. Priority Date: 01/11/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Liu, Peng, Shi, Yu, Soong, Frank Kao-ping
• Granted Patent: US 8,355,917 B2
• Time in Patent Office: Days
• US Class Current: 704/254
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams

Abstract

A representation of a speech signal is received and is decoded to identify a sequence of position-dependent phonetic tokens wherein each token comprises a phone and a position indicator that indicates the position of the phone within a syllable.

Claims

1. A method comprising:

identifying a position-dependent phonetic description of each word in a word language model, each position-dependent phonetic description comprising at least one position-dependent phonetic token, each position-dependent phonetic token comprising a phone and a position identifier that identifies a position within a syllable;

using probabilities for words and probabilities for sequences of words in the word language model to set probabilities for position-dependent phonetic tokens and probabilities for sequences of position-dependent tokens to construct a position-dependent phonetic language model; and

storing the position-dependent phonetic language model.

2. The method of claim 1 wherein setting probabilities comprises developing within-word counts for position-dependent phonetic tokens and for sequences of position-dependent phonetic tokens that are bounded within individual words based on unigram probabilities of the words that the position-dependent phonetic tokens are bound within.

3. The method of claim 2 wherein setting probabilities comprises developing cross-word counts for sequences of position-dependent phonetic tokens that span multiple words based on probabilities of the sequences of multiple words that the sequences of position-dependent phonetic tokens span.

4. The method of claim 3 wherein setting probabilities further comprises using the within-word counts and the cross-word counts to determine a joint probability for position-dependent phonetic tokens in a sequence of position-dependent phonetic tokens.

5. The method of claim 1 further comprising using the position-dependent phonetic language model to identify a sequence of position-dependent phonetic tokens from a speech signal.

6. The method of claim 5 further comprising using the sequence to annotate a lexicon with a pronunciation for at least one symbol that is not found in a written language.

7. The method of claim 5 further comprising using the sequence of position-dependent phonetic tokens as part of discriminative training of an acoustic model

8. A hardware computer storage medium encoded with a computer program, causing the computer to execute steps comprising:

using probabilities for words and probabilities for sequences of words in a word language model to set probabilities for position-dependent phonetic tokens and probabilities for sequences of position-dependent phonetic tokens to construct a position-dependent phonetic language model; and

storing the position-dependent phonetic language model.

9. The hardware computer storage medium of claim 8 wherein setting probabilities for sequences of position-dependent phonetic tokens comprises developing cross-word counts for sequences of position-dependent phonetic tokens that span multiple words based on probabilities of sequences of multiple words that the sequences of position-dependent phonetic tokens span.

10. The hardware computer storage medium of claim 9 wherein setting probabilities for position-dependent phonetic tokens and sequences of position-dependent phonetic tokens comprises developing within-word counts for position-dependent phonetic tokens and for sequences of position-dependent phonetic tokens that are bounded within individual words based on unigram probabilities of the words that the position-dependent phonetic tokens are bound within.

11. The hardware computer storage medium of claim 10 wherein setting probabilities further comprises using the within-word counts and the cross-word counts to determine a joint probability for position-dependent phonetic tokens in a sequence of position-dependent phonetic tokens.

12. The hardware computer storage medium of claim 8 further comprising using the position-dependent phonetic language model to identify a sequence of position-dependent phonetic tokens from a speech signal.

13. The hardware computer storage medium of claim 12 further comprising using the sequence of position-dependent phonetic tokens identified from the speech signal to annotate a lexicon with a pronunciation for at least one symbol that is not found in a written language.

14. The hardware computer storage medium of claim 12 further comprising using the sequence of position-dependent phonetic tokens identified from the speech signal as part of discriminative training of an acoustic model.

15. A computer-implemented method comprising:

setting probabilities for sequences of position-dependent phonetic tokens through steps comprising developing cross-word counts for sequences of position-dependent phonetic tokens that span multiple words based on probabilities of sequences of multiple words that the sequences of position-dependent phonetic tokens span; and

storing the probabilities for sequences of position-dependent phonetic tokens as part of a position-dependent phonetic language model.

16. The computer-implemented method of claim 15 wherein setting probabilities for sequences of position-dependent phonetic tokens further comprises developing within-word counts for sequences of position-dependent phonetic tokens that are bounded within individual words based on unigram probabilities of the words that the sequences of position-dependent phonetic tokens are bound within.

17. The computer-implemented method of claim 15 wherein setting probabilities for sequences of position-dependent phonetic tokens further comprises using the within-word counts and the cross-word counts to determine a joint probability for position-dependent phonetic tokens in a sequence of position-dependent phonetic tokens.

18. The computer-implemented method of claim 15 further comprising using the position-dependent phonetic language model to identify a sequence of position-dependent phonetic tokens from a speech signal.

19. The computer-implemented method of claim 18 further comprising using the sequence of position-dependent phonetic tokens identified from the speech signal to annotate a lexicon with a pronunciation for at least one symbol that is not found in a written language.

20. The computer-implemented method of claim 18 further comprising using the sequence of position-dependent phonetic tokens identified from the speech signal as part of discriminative training of an acoustic model.