System and method for recognizing speech with dialect grammars

• US 9,082,405 B2
• Filed: 11/26/2014
• Issued: 07/14/2015
• Est. Priority Date: 12/23/2008
• Status: Active Grant

• Current Assignee: Interactions, LLC
• Original Assignee: Interactions, LLC
• Inventors: Pulz, Gregory, Blanchard, Harry E., Lewis, Steven H., Zhang, Lan
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US14/554,164
• Publication Number:
  US 20150081305A1
• Time in Patent Office: 230 Days
• Field of Search: 704/8, 704/231, 704/257, 704/E15.04
• US Class Current: 1/1
• 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:

for each dialect in a plurality of dialects identified within a speech utterance, selecting, via a processor, a corresponding dialect grammar, to yield a plurality of dialect grammars;

blending, via the processor, the plurality of dialect grammars, to yield a blended dialect grammar; and

recognizing the speech utterance using the blended dialect grammar.

2. The method of claim 1, wherein selection of the corresponding dialect grammar is based on a similarity of the dialect to the corresponding dialect grammar, wherein the similarity is based on phoneme usage in the dialect and the corresponding dialect grammar.

3. The method of claim 2, wherein selection of the corresponding dialect grammar is further based on a user profile.

4. The method of claim 3, wherein the user profile is associated with a grammar personalized for a user associated with the user profile and the speech utterance.

5. The method of claim 1, wherein selection of the corresponding dialect grammar is based on a user location.

6. The method of claim 1, wherein the blending of the plurality of dialect grammars further comprises blending elements of each corresponding dialect grammar in the plurality of dialect grammars based on a respective score of each corresponding dialect grammar.

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

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

9. The method of claim 1, wherein each dialect grammar of the plurality of dialect grammars is associated with parameters comprising one of vocabulary and sentence structure.

10. A system comprising:

a processor; and

a computer-readable storage medium having instructions stored which, when executed by the processor, result in the processor performing operations comprising;

for each dialect in a plurality of dialects identified within a speech utterance, selecting a corresponding dialect grammar, to yield a plurality of dialect grammars;

blending the plurality of dialect grammars, to yield a blended dialect grammar; and

recognizing the speech utterance using the blended dialect grammar.

11. The system of claim 10, wherein selection of the corresponding dialect grammar is based on a similarity of the dialect to the corresponding dialect grammar, wherein the similarity is based on phoneme usage in the dialect and the corresponding dialect grammar.

12. The system of claim 11, wherein selection of the corresponding dialect 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 a user associated both with the user profile and the speech utterance.

14. The system of claim 10, wherein selection of the corresponding dialect grammar is based on a user location.

15. The system of claim 10, wherein the blending of the plurality of dialect grammars further comprises blending elements of each corresponding dialect grammar in the plurality of dialect grammars based on a respective score of each corresponding dialect grammar.

16. The system of claim 10, the computer-readable storage medium having additional instructions stored which, when executed by the processor, result in operations comprising recognizing initial speech with a generic grammar until the blended dialect grammar is generated.

17. The system of claim 10, wherein the plurality of dialect grammars are domain specific.

18. The system of claim 10, wherein each dialect grammar of the plurality of dialect grammars is associated with parameters comprising one of vocabulary and sentence structure.

19. A computer-readable storage device having instructions stored which, when executed by a computing device, result in the computing device performing operations comprising:

for each dialect in a plurality of dialects identified within a speech utterance, selecting a corresponding dialect grammar, to yield a plurality of dialect grammars;

blending the plurality of dialect grammars, to yield a blended dialect grammar; and

recognizing the speech utterance using the blended dialect grammar.

20. The computer-readable storage device of claim 19, wherein selection of the corresponding dialect grammar is based on a similarity of the dialect to the corresponding dialect grammar, wherein the similarity is based on phoneme usage in the dialect and the corresponding dialect grammar.