System and method for recognizing speech with dialect grammars

• US 8,635,068 B2
• Filed: 12/23/2008
• Issued: 01/21/2014
• 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, Blanchard, Harry E., Lewis, Steven H., Zhang, Lan
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US12/343,057
• Publication Number:
  US 20100161337A1
• Time in Patent Office: 1,855 Days
• Field of Search: 704/8, 704/231, 704/257, 704/E15.04
• 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 method comprising:

receiving a speech utterance from a user;

performing an analysis, via a processor, of the speech utterance to determine a first speech dialect and a second speech dialect;

selecting a first dialect grammar from a plurality of optimized dialect grammars based on a similarity of the first dialect grammar to the first speech dialect;

selecting a second dialect grammar from the plurality of optimized dialect grammars based on a similarity of the second dialect grammar to the second speech dialect;

blending the first dialect grammar and the second dialect grammar, to yield a blended dialect grammar; and

recognizing, with the blended dialect grammar, the speech utterance.

2. The method of claim 1, wherein selecting at least one of the first dialect grammar and the second dialect grammar is further based on a user profile.

3. The 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 method of claim 1, wherein blending the first dialect grammar and the second dialect grammar comprises blending elements of each grammar based on a respective score for each selected grammar.

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

6. The method of claim 1, wherein each grammar is associated with predefined parameters comprising at least one of pronunciation differences, vocabulary, and sentence structure.

7. The method of claim 1, wherein the plurality of optimized dialect grammars are domain specific.

8. The method of claim 1, further comprising recognizing initial speech with a generic grammar until the blended dialect grammar is yielded.

9. The method of claim 1, wherein selecting the first dialect grammar and the second dialect grammar from a plurality of optimized dialect grammars is further based on a certainty threshold.

10. A system comprising:

a processor;

a memory storing instructions for controlling the processor to perform a method comprising;

receiving a speech utterance from a user;

performing an analysis of the speech utterance to determine a first speech dialect and a second speech dialect;

selecting a first dialect grammar from a plurality of optimized dialect grammars based on a similarity of the first dialect grammar to the first speech dialect;

selecting a second dialect grammar from the plurality of optimized dialect grammars based on a similarity of the second dialect grammar to the second speech dialect;

blending the first dialect grammar and the second dialect grammar, to yield a blended dialect grammar; and

recognizing, with the blended dialect grammar.

11. The system of claim 10, the method further comprising selecting at least one of the first dialect grammar and the second dialect grammar based on a user profile.

12. The system of claim 11, wherein the user profile is associated with a grammar personalized for the user, the method further comprising selecting the grammar personalized for the user.

13. The system of claim 11, wherein blending the first dialect grammar and the second dialect grammar further comprises blending elements of each grammar based on a respective score for each selected grammar.

14. A non-transitory computer-readable storage medium storing a computer program having instructions for controlling a computing device to perform a method comprising:

receiving a speech utterance from a user;

performing an analysis of the speech utterance to determine a first speech dialect and a second speech dialect;

selecting a first dialect grammar from a plurality of optimized dialect grammars based on a similarity of the first dialect grammar to the first speech dialect;

selecting a second dialect grammar from the plurality of optimized dialect grammars based on a similarity of the second dialect grammar to the second speech dialect;

blending the first dialect grammar and the second dialect grammar, to yield a blended dialect grammar; and

recognizing, with the blended dialect grammar, the speech utterance.

15. The non-transitory computer-readable storage medium of claim 14, wherein selecting at least one of the first dialect grammar and the second dialect grammar is further based on a user profile.

16. The non-transitory computer-readable storage medium of claim 15, wherein the user profile is associated with a grammar personalized for the user, the method further comprising selecting the grammar personalized for the user.

17. The non-transitory computer-readable storage medium of claim 14, wherein blending the plurality of selected grammars comprises blending elements in the each dialect grammars based on a respective score for each selected grammar.