SYSTEM AND METHOD FOR RECOGNIZING SPEECH WITH DIALECT GRAMMARS

• US 20100161337A1
• Filed: 12/23/2008
• Published: 06/24/2010
• Est. Priority Date: 12/23/2008
• Status: Active Grant

• Current Assignee: Interactions, LLC
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: PULZ, Gregory, ZHANG, Lan, LEWIS, Steven H., BLANCHARD, Harry E.
• Granted Patent: US 8,635,068 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules

Abstract

Disclosed herein are systems, computer-implemented methods, and computer-readable media for recognizing speech. The method includes receiving speech from a user, perceiving at least one speech dialect in the received speech, selecting at least one grammar from a plurality of optimized dialect grammars based on at least one score associated with the perceived speech dialect and the perceived at least one speech dialect, and recognizing the received speech with the selected at least one grammar. Selecting at least one grammar can be further based on a user profile. Multiple grammars can be blended. Predefined parameters can include pronunciation differences, vocabulary, and sentence structure. Optimized dialect grammars can be domain specific. The method can further include recognizing initial received speech with a generic grammar until an optimized dialect grammar is selected. Selecting at least one grammar from a plurality of optimized dialect grammars can be based on a certainty threshold.

Claims

1. A computer-implemented method of recognizing speech, the method comprising:

receiving speech from a user;

perceiving at least one speech dialect in the received speech;

selecting at least one grammar from a plurality of optimized dialect grammars based on at least one score associated with the perceived speech dialect and the perceived at least one speech dialect; and

recognizing the received speech with the selected at least one grammar.

2. The computer-implemented method of claim 1, wherein selecting at least one grammar is further based on a user profile.

3. The computer-implemented method of claim 2, wherein the user profile is associated with a grammar personalized for the user, the method further comprising selecting the grammar personalized for the user.

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

blending two or more selected grammars when multiple grammars are selected; and

recognizing the received speech with the blended two or more selected grammars.

5. The computer-implemented method of claim 4, wherein blending two or more selected grammars comprises blending elements in the two or more selected grammars based on a respective score for each grammar.

6. The computer-implemented method of claim 1, wherein selecting at least one grammar is further based on a user location.

7. The computer-implemented method of claim 1, wherein predefined parameters comprise at least one of pronunciation differences, vocabulary, and sentence structure.

8. The computer-implemented method of claim 1, wherein optimized dialect grammars are domain specific.

9. The computer-implemented method of claim 1, the method further comprising recognizing initial received speech with a generic grammar until an optimized dialect grammar is selected.

10. The computer-implemented method of claim 1, wherein selecting at least one grammar from a plurality of optimized dialect grammars is based on a certainty threshold.

11. A system for recognizing speech, the system comprising:

a module configured to receive speech from a user;

a module configured to perceive at least one speech dialect in the received speech;

a module configured to select at least one grammar from a plurality of optimized dialect grammars based on at least one score associated with the perceived speech dialect and the perceived at least one speech dialect; and

a module configured to recognize the received speech with the selected at least one grammar.

12. The system of claim 11, wherein the module configured to select at least one grammar is further based on a user profile.

13. The system of claim 12, wherein the user profile is associated with a grammar personalized for the user, the system further comprising a module configured to select the grammar personalized for the user.

14. The system of claim 11, the system further comprising:

a module configured to blend two or more selected grammars when multiple grammars are selected; and

a module configured to recognize the received speech with the blended two or more selected grammars.

15. The system of claim 14, wherein a module configured to blend two or more selected grammars further blends elements in the two or more selected grammars based on a respective score for each grammar.

16. A tangible computer-readable medium storing a computer program having instructions for recognizing speech, the instructions comprising:

receiving speech from a user;

perceiving at least one speech dialect in the received speech;

selecting at least one grammar from a plurality of optimized dialect grammars based on at least one score associated with the perceived speech dialect and the perceived at least one speech dialect; and

recognizing the received speech with the selected at least one grammar.

17. The tangible computer-readable medium of claim 16, wherein selecting at least one grammar is further based on a user profile.

18. The tangible computer-readable medium of claim 17, wherein the user profile is associated with a grammar personalized for the user, the method further comprising selecting the grammar personalized for the user.

19. The tangible computer-readable medium of claim 16, the instructions further comprising:

blending two or more selected grammars when multiple grammars are selected; and

recognizing the received speech with the blended two or more selected grammars.

20. The tangible computer-readable medium of claim 19, wherein blending two or more selected grammars comprises blending elements in the two or more selected grammars based on a respective score for each grammar.