Determining hotword suitability

• US 10,714,096 B2
• Filed: 05/16/2018
• Issued: 07/14/2020
• Est. Priority Date: 07/03/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Rubin, Andrew, Schalkwyk, Johan, San Martin, Maria Carolina Parada
• Primary Examiner(s): Ortiz-Sanchez, Michael
• Application Number:
  US15/981,376
• Publication Number:
  US 20180336906A1
• Time in Patent Office: 790 Days
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/46 by designing passwords or checking the strength of passwords
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• 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 17/24 the user being prompted to utter a password or a predefined phrase
• CPC Class Codes: G10L 2015/0638 Interactive procedures
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/225 Feedback of the input speech
• CPC Class Codes: G10L 25/51 for comparison or discrimination

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining hotword suitability. In one aspect, a method includes receiving speech data that encodes a candidate hotword spoken by a user, evaluating the speech data or a transcription of the candidate hotword, using one or more predetermined criteria, generating a hotword suitability score for the candidate hotword based on evaluating the speech data or a transcription of the candidate hotword, using one or more predetermined criteria, and providing a representation of the hotword suitability score for display to the user.

Claims

1. A method performed by one or more computing devices:

receiving, by the one or more computing devices, speech data that encodes an utterance of a candidate hotword by a user, the candidate hotword comprising a word or phrase;

evaluating, by the one or more computing devices, the speech data or a transcription of the speech data using one or more hotword suitability criteria;

determining, by the one or more computing devices and based on the evaluation, that the candidate hotword satisfies the one or more hotword suitability criteria; and

in response to determining that the candidate hotword satisfies the one or more hotword suitability criteria, accepting the candidate hotword as a hotword for at least one computing device associated with the user and configuring the at least one computing device to enter a state to receive voice commands in response to utterances of the hotword.

2. The method of claim 1, wherein evaluating the speech data or a transcription of the speech data comprises determining a hotword suitability score for the candidate hotword;

and

wherein determining that the candidate hotword satisfies the one or more hotword suitability criteria comprises determining that the hotword suitability score satisfies a predetermined threshold.

3. The method of claim 2, wherein determining a hotword suitability score for the candidate hotword comprises:

generating a feature score for the speech data or of a transcription of the speech data, for each of two or more predetermined criteria;

aggregating the feature scores; and

generating a hotword suitability score based on the aggregated feature scores.

4. The method of claim 1, wherein evaluating the speech data or a transcription of the speech data comprises evaluating a length of the speech data representing the utterance of the candidate hotword.

5. The method of claim 1, wherein evaluating the speech data or a transcription of the speech data comprises evaluating a quantity of syllables or phones in a representation of the candidate hotword.

6. The method of claim 1, wherein evaluating the speech data or a transcription of the speech data comprises evaluating an edit distance between the transcription of the candidate hotword and one or more other words that share a same language as the candidate hotword.

7. The method of claim 1, wherein evaluating the speech data or a transcription of the speech data comprises evaluating a quantity of pronunciations specified for the candidate hotword.

8. The method of claim 1, wherein evaluating the speech data or a transcription of the speech data comprises determining that one or more particular linguistic units occur in the transcription of the speech data.

9. The method of claim 1, wherein evaluating the speech data or a transcription of the speech data comprises evaluating an extent to which pronunciation of the candidate hotword varies among multiple utterances of the candidate hotword by the user.

10. A system comprising:

one or more computing devices; and

one or more computer-readable media storing instructions that, when executed by the one or more computing devices, cause the one or more computing devices to perform operations comprising;

receiving, by the one or more computing devices, speech data that encodes an utterance of a candidate hotword by a user, the candidate hotword comprising a word or phrase;

evaluating, by the one or more computing devices, the speech data or a transcription of the speech data using one or more hotword suitability criteria;

determining, by the one or more computing devices and based on the evaluation, that the candidate hotword satisfies the one or more hotword suitability criteria; and

in response to determining that the candidate hotword satisfies the one or more hotword suitability criteria, accepting the candidate hotword as a hotword for at least one computing device associated with the user and configuring the at least one computing device to enter a state to receive voice commands in response to utterances of the hotword.

11. The system of claim 10, wherein evaluating the speech data or a transcription of the speech data comprises determining a hotword suitability score for the candidate hotword;

and

wherein determining that the candidate hotword satisfies the one or more hotword suitability criteria comprises determining that the hotword suitability score satisfies a predetermined threshold.

12. The system of claim 11, wherein determining a hotword suitability score for the candidate hotword comprises:

generating a feature score for the speech data or of a transcription of the speech data, for each of two or more predetermined criteria;

aggregating the feature scores; and

generating a hotword suitability score based on the aggregated feature scores.

13. The system of claim 10, wherein evaluating the speech data or a transcription of the speech data comprises evaluating a length of the speech data representing the utterance of the candidate hotword.

14. A method performed by one or more computing devices:

receiving, by the one or more computing devices, speech data that encodes an utterance of a candidate hotword by a user, the candidate hotword comprising a word or phrase;

evaluating, by the one or more computing devices, the speech data or a transcription of the speech data using one or more hotword suitability criteria;

determining, by the one or more computing devices and based on the evaluation, that the candidate hotword does not satisfy the one or more hotword suitability criteria; and

in response to determining that the candidate hotword does not satisfy the one or more hotword suitability criteria, providing, for output by a computing device associated with the user, an indication that the candidate hotword is not accepted as a custom hotword.

15. The method of claim 14, wherein evaluating the speech data or a transcription of the speech data comprises determining a hotword suitability score for the candidate hotword;

and

wherein determining that the candidate hotword does not satisfy the one or more hotword suitability criteria comprises determining that the hotword suitability score does not satisfy a predetermined threshold.

16. The method of claim 15, wherein determining a hotword suitability score for the candidate hotword comprises:

generating a feature score for the speech data or of a transcription of the speech data, for each of two or more predetermined criteria;

aggregating the feature scores; and

generating a hotword suitability score based on the aggregated feature scores.

17. The method of claim 14, wherein evaluating the speech data or a transcription of the speech data comprises evaluating a length of the speech data representing the utterance of the candidate hotword.

18. The method of claim 14, wherein evaluating the speech data or a transcription of the speech data comprises evaluating a quantity of syllables or phones in a representation of the candidate hotword.

19. The method of claim 14, wherein evaluating the speech data or a transcription of the speech data comprises evaluating an edit distance between the transcription of the candidate hotword and one or more other words that share a same language as the candidate hotword.

20. The method of claim 14, wherein evaluating the speech data or a transcription of the speech data comprises evaluating a quantity of pronunciations specified for the candidate hotword.

21. A system comprising:

one or more computing devices; and

one or more computer-readable media storing instructions that, when executed by the one or more computing devices, cause the one or more computing devices to perform operations comprising;

receiving, by the one or more computing devices, speech data that encodes an utterance of a candidate hotword by a user, the candidate hotword comprising a word or phrase;

evaluating, by the one or more computing devices, the speech data or a transcription of the speech data using one or more hotword suitability criteria;

determining, by the one or more computing devices and based on the evaluation, that the candidate hotword does not satisfy the one or more hotword suitability criteria; and

in response to determining that the candidate hotword does not satisfy the one or more hotword suitability criteria, providing, for output by a computing device associated with the user, an indication that the candidate hotword is not accepted as a custom hotword.