Determining hotword suitability
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.
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.