MULTIPLE SPEECH LOCALE-SPECIFIC HOTWORD CLASSIFIERS FOR SELECTION OF A SPEECH LOCALE

• US 20150221305A1
• Filed: 02/05/2014
• Published: 08/06/2015
• Est. Priority Date: 02/05/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Sharifi, Matthew
• Granted Patent: US 9,589,564 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for recognizing speech in an utterance. The methods, systems, and apparatus include actions of receiving an utterance and obtaining acoustic features from the utterance. Further actions include providing the acoustic features from the utterance to multiple speech locale-specific hotword classifiers. Each speech locale-specific hotword classifier (i) may be associated with a respective speech locale, and (ii) may be configured to classify audio features as corresponding to, or as not corresponding to, a respective predefined term. Additional actions may include selecting a speech locale for use in transcribing the utterance based on one or more results from the multiple speech locale-specific hotword classifiers in response to providing the acoustic features from the utterance to the multiple speech locale-specific hotword classifiers. Further actions may include selecting parameters for automated speech recognition based on the selected speech locale.

Claims

1. A computer-implemented method, comprising:

receiving an utterance;

obtaining acoustic features from the utterance;

providing the acoustic features from the utterance to multiple speech locale-specific hotword classifiers, wherein each speech locale-specific hotword classifier (i) is associated with a respective speech locale, and (ii) is configured to classify acoustic features as either corresponding to, or as not corresponding to, a respective predefined term without one or more of transcribing or semantically interpreting the acoustic features;

selecting a speech locale for use in transcribing the utterance based on one or more results from the multiple speech locale-specific hotword classifiers in response to providing the acoustic features from the utterance to the multiple speech locale-specific hotword classifiers; and

selecting parameters for automated speech recognition based on the selected speech locale.

2. The method of claim 1, wherein two or more of the speech locale-specific hotword classifiers are associated with different speech locales, and are associated with the same predefined term.

3. The method of claim 1, wherein two or more of the speech locale-specific hotword classifiers are associated with different speech locales, and are associated with different predefined terms.

4. The method of claim 1, comprising:

transcribing the utterance based on the selected parameters.

5. The method of claim 1, wherein providing the acoustic features from the utterance to multiple speech locale-specific hotword classifiers comprises:

providing the acoustic features to a particular speech locale-specific hotword classifier that is associated with multiple other speech locale-specific hotword classifiers; and

determining to provide the acoustic features to the multiple other speech locale-specific hotword classifiers based on a result from the particular speech locale-specific hotword classifier.

6. The method of claim 5, wherein the particular speech locale-specific hotword classifier comprises a speech locale-specific hotword classifier for a particular language and the multiple other speech locale-specific hotword classifiers associated with the particular speech locale-specific hotword classifier comprise speech locale-specific hotword classifiers for particular dialects for the particular language.

7. The method of claim 1, wherein providing the acoustic features from the utterance to multiple speech locale-specific hotword classifiers comprises selecting a subset of speech locale-specific hotword classifiers to provide the acoustic features from a set of speech locale-specific hotword classifiers based on previous selections of speech locales used to transcribe previously received utterances.

8. The method of claim 1, wherein selecting a speech locale for use in transcribing the utterance based on one or more results from the multiple speech locale-specific hotword classifiers in response to providing the acoustic features from the utterance to the multiple speech locale-specific hotword classifiers comprises:

obtaining speech locale-specific hotword confidence scores from the speech locale-specific hotword classifiers;

determining a highest speech locale-specific hotword confidence score from the speech locale-specific hotword confidence scores; and

selecting a speech locale associated with the determined highest speech locale-specific hotword confidence score.

9. The method of claim 1, wherein selecting a speech locale for use in transcribing the utterance based on one or more results from the multiple speech locale-specific hotword classifiers in response to providing the acoustic features from the utterance to the multiple speech locale-specific hotword classifiers comprises:

obtaining speech locale-specific hotword confidence scores from the speech locale-specific hotword classifiers;

determining a predetermined number of highest speech locale-specific hotword confidence scores from the speech locale-specific hotword confidence scores;

selecting speech locales associated with the determined highest speech locale-specific hotword confidence scores; and

for each of the selected speech locales, obtaining a recognition confidence score from an automated speech recognizer,

wherein obtaining a transcription of the utterance based on the selected speech locale comprises selecting a transcription corresponding to a highest combination of the speech locale-specific hotword confidence scores and the recognition confidence scores.

21. The method of claim 1, wherein without one or more of transcribing or semantically interpreting the acoustic features comprises without transcribing the acoustic features to one or more of a word or sub-word level.

22. The method of claim 1, wherein receiving an utterance comprises receiving an utterance in a first mode where one or more of transcribing or semantically interpreting acoustic features obtained from utterances is not performed, the method comprising:

entering a second mode where one or more of transcribing or semantically interpreting acoustic features obtained from utterances is performed based on one or more results from the multiple speech locale-specific hotword classifiers in response to providing the acoustic features from the utterance to the multiple speech locale-specific hotword classifiers.

23. The method of claim 1, wherein the acoustic features comprise mel-frequency cepstrum coefficients.

10. A system comprising:

one or more computers; and

one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving an utterance;

obtaining acoustic features from the utterance;

providing the acoustic features from the utterance to multiple speech locale-specific hotword classifiers, wherein each speech locale-specific hotword classifier (i) is associated with a respective speech locale, and (ii) is configured to classify acoustic features as either corresponding to, or as not corresponding to, a respective predefined term without one or more of transcribing or semantically interpreting the acoustic features;

selecting a speech locale for use in transcribing the utterance based on one or more results from the multiple speech locale-specific hotword classifiers in response to providing the acoustic features from the utterance to the multiple speech locale-specific hotword classifiers; and

selecting parameters for automated speech recognition based on the selected speech locale.

11. The system of claim 10, wherein two or more of the speech locale-specific hotword classifiers are associated with different speech locales, and are associated with the same predefined term.

12. The system of claim 10, wherein two or more of the speech locale-specific hotword classifiers are associated with different speech locales, and are associated with different predefined terms.

13. The system of claim 10, comprising:

transcribing the utterance based on the selected parameters.

14. The system of claim 10, wherein providing the acoustic features from the utterance to multiple speech locale-specific hotword classifiers comprises:

providing the acoustic features to a particular speech locale-specific hotword classifier that is associated with multiple other speech locale-specific hotword classifiers; and

determining to provide the acoustic features to the multiple other speech locale-specific hotword classifiers based on a result from the particular speech locale-specific hotword classifier.

15. The system of claim 14, wherein the particular speech locale-specific hotword classifier comprises a speech locale-specific hotword classifier for a particular language and the multiple other speech locale-specific hotword classifiers associated with the particular speech locale-specific hotword classifier comprise speech locale-specific hotword classifiers for particular dialects for the particular language.

16. A non-transitory computer-readable medium storing instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving an utterance;

obtaining acoustic features from the utterance;

providing the acoustic features from the utterance to multiple speech locale-specific hotword classifiers, wherein each speech locale-specific hotword classifier (i) is associated with a respective speech locale, and (ii) is configured to classify acoustic features as either corresponding to, or as not corresponding to, a respective predefined term without one or more of transcribing or semantically interpreting the acoustic features;

selecting a speech locale for use in transcribing the utterance based on one or more results from the multiple speech locale-specific hotword classifiers in response to providing the acoustic features from the utterance to the multiple speech locale-specific hotword classifiers; and

selecting parameters for automated speech recognition based on the selected speech locale.

17. The medium of claim 16, wherein two or more of the speech locale-specific hotword classifiers are associated with different speech locales, and are associated with the same predefined term.

18. The medium of claim 16, wherein two or more of the speech locale-specific hotword classifiers are associated with different speech locales, and are associated with different predefined terms.

19. The medium of claim 16, comprising:

transcribing the utterance based on the selected parameters.

20. The medium of claim 16, wherein providing the acoustic features from the utterance to multiple speech locale-specific hotword classifiers comprises:

providing the acoustic features to a particular speech locale-specific hotword classifier that is associated with multiple other speech locale-specific hotword classifiers; and

determining to provide the acoustic features to the multiple other speech locale-specific hotword classifiers based on a result from the particular speech locale-specific hotword classifier.