SYSTEM AND METHOD FOR HANDLING MISSING SPEECH DATA

• US 20100131264A1
• Filed: 11/21/2008
• Published: 05/27/2010
• Est. Priority Date: 11/21/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Ljolje, Andrej, Conkie, Alistair D.
• Granted Patent: US 8,751,229 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units
• CPC Class Codes: G10L 25/87 Detection of discrete points within a voice signal

Abstract

Disclosed herein are systems, computer-implemented methods, and tangible computer-readable media for handling missing speech data. The computer-implemented method includes receiving speech with a missing segment, generating a plurality of hypotheses for the missing segment, identifying a best hypothesis for the missing segment, and recognizing the received speech by inserting the identified best hypothesis for the missing segment. In another method embodiment, the final step is replaced with synthesizing the received speech by inserting the identified best hypothesis for the missing segment. In one aspect, the method further includes identifying a duration for the missing segment and generating the plurality of hypotheses of the identified duration for the missing segment. The step of identifying the best hypothesis for the missing segment can be based on speech context, a pronouncing lexicon, and/or a language model. Each hypothesis can have an identical acoustic score.

Claims

1. A computer-implemented method of handling missing speech data, the method comprising:

receiving speech with a missing segment;

generating a plurality of hypotheses for the missing segment;

identifying a best hypothesis for the missing segment; and

recognizing the received speech by inserting the identified best hypothesis for the missing segment.

2. The computer-implemented method of claim 1, the method further comprising:

identifying a duration for the missing segment; and

generating the plurality of hypotheses of the identified duration for the missing segment.

3. The computer-implemented method of claim 1, wherein identifying the best hypothesis for the missing segment is based on speech context.

4. The computer-implemented method of claim 1, wherein identifying the best hypothesis for the missing segment is based on a pronouncing lexicon.

5. The computer-implemented method of claim 1, wherein identifying the best hypothesis for the missing segment is based on a language model.

6. The computer-implemented method of claim 1, wherein each of the plurality of hypotheses has an identical acoustic score.

7. The computer-implemented method of claim 6, wherein the identical acoustic score reflects a certainty of the hypotheses.

16. The system of claim 1, the system further comprising:

a module configured to identify a duration for the missing segment; and

a module configured to generate the plurality of hypotheses of the identified duration for the missing segment.

17. The system of claim 1, wherein identifying the best hypothesis for the missing segment is based on speech context.

18. The system of claim 1, wherein identifying the best hypothesis for the missing segment is based on a pronouncing lexicon.

19. The system of claim 1, wherein identifying the best hypothesis for the missing segment is based on a language model.

20. The system of claim 1, wherein each of the plurality of hypotheses has an identical acoustic score.

8. A computer-implemented method of handling missing speech data, the method comprising:

receiving speech with a missing segment;

generating a plurality of hypotheses for the missing segment;

identifying a best hypothesis for the missing segment; and

synthesizing the received speech by inserting the identified best hypothesis for the missing segment.

9. The computer-implemented method of claim 8, the method further comprising:

identifying a duration for the missing segment; and

generating the plurality of hypotheses of the identified duration for the missing segment.

10. The computer-implemented method of claim 8, wherein identifying the best hypothesis for the missing segment is based on speech context.

11. The computer-implemented method of claim 8, wherein identifying the best hypothesis for the missing segment is based on a pronouncing lexicon.

12. The computer-implemented method of claim 8, wherein identifying the best hypothesis for the missing segment is based on a language model.

13. The computer-implemented method of claim 8, wherein each of the plurality of hypotheses has an identical acoustic score.

14. The computer-implemented method of claim 13, wherein the identical acoustic score reflects a certainty of the hypotheses.

15. A system for handling missing speech data, the system comprising:

a module configured to receive speech with a missing segment;

a module configured to generate a plurality of hypotheses for the missing segment;

a module configured to identify a best hypothesis for the missing segment; and

a module configured to recognize the received speech by inserting the identified best hypothesis for the missing segment.