Segment-based speaker verification using dynamically generated phrases

1. A computer-implemented method comprising:

receiving a request for a verification phrase for verifying an identity of a user;

in response to receiving the request for the verification phrase for verifying the identity of the user, identifying subwords to be included in the verification phrase;

in response to identifying the subwords to be included in the verification phrase, obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase, based on a predetermined criteria; and

providing the verification phrase as a response to the request for the verification phrase for verifying the identity of the user,

wherein identifying subwords to be included in the verification phrase comprises identifying candidate subwords, for which no stored acoustic data is associated with the user, as one or more of the subwords to be included in the verification phrase.

2. The method of claim 1 , wherein identifying subwords to be included in the verification phrase comprises identifying candidate subwords, for which stored acoustic data is associated with the user, as one or more of the subwords to be included in the verification phrase.

3. The method of claim 1 , wherein obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase comprises:

determining that a particular identified subword is particularly sound discriminative; and

in response to determining that the particular identified subword is particularly sound discriminative, obtaining a candidate phrase that includes the particular identified subword that is determined to be particularly sound discriminative.

4. The method of claim 1 , wherein obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase comprises:

obtaining multiple candidate phrases including the candidate that includes at least some of the identified subwords;

determining that the candidate phrase includes at least some of the identified subwords; and

in response to determining that the candidate phrase includes at least some of the identified subwords, selecting the determined candidate phrase as the candidate phrase that includes at least some of the identified subwords from among the multiple candidate phrases.

5. The method of claim 1 , further comprising:

obtaining acoustic data representing the user speaking the verification phrase;

determining that the obtained acoustic data matches stored acoustic data for the user; and

in response to determining that the obtained acoustic data matches stored acoustic data for the user, classifying the user as the user.

6. The method of claim 5 , wherein determining that the obtained acoustic data matches stored acoustic data for the user comprises determining that stored acoustic data for the at least some of the identified subwords in the verification phrase match obtained acoustic data that correspond to the at least some of the identified subwords in the verification phrase.

7. The method of claim 6 , wherein obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase comprises obtaining a candidate phrase that includes at least one candidate subword for which stored acoustic data is associated with the user and at least one candidate subword for which no stored acoustic data is associated with the user.

8. The method of claim 7 , further comprising storing acoustic data from the obtained acoustic data that corresponds to the identified candidate subwords, for which no stored acoustic data is associated with the user, in association with the user.

9. 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 a request for a verification phrase for verifying an identity of a user;

in response to receiving the request for the verification phrase for verifying the identity of the user, identifying subwords to be included in the verification phrase;

in response to identifying the subwords to be included in the verification phrase, obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase, based on a predetermined criteria, and

providing the verification phrase as a response to the request for the verification phrase for verifying the identity of the user,

wherein identifying subwords to be included in the verification phrase comprises identifying candidate subwords, for which no stored acoustic data is associated with the user, as one or more of the subwords to be included in the verification phrase.

10. The system of claim 9 , wherein identifying subwords to be included in the verification phrase comprises identifying candidate subwords, for which stored acoustic data is associated with the user, as one or more of the subwords to be included in the verification phrase.

11. The system of claim 9 , wherein obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase comprises:

determining that a particular identified subword is particularly sound discriminative; and

in response to determining that the particular identified subword is particularly sound discriminative, obtaining a candidate phrase that includes the particular identified subword that is determined to be particularly sound discriminative.

12. The system of claim 9 , wherein obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase comprises:

obtaining multiple candidate phrases including the candidate that includes at least some of the identified subwords;

determining that the candidate phrase includes at least some of the identified subwords; and

in response to determining that the candidate phrase includes at least some of the identified subwords, selecting the determined candidate phrase as the candidate phrase that includes at least some of the identified subwords from among the multiple candidate phrases.

13. The system of claim 9 , wherein the operations further comprise:

obtaining acoustic data representing the user speaking the verification phrase;

determining that the obtained acoustic data matches stored acoustic data for the user; and

in response to determining that the obtained acoustic data matches stored acoustic data for the user, classifying the user as the user.

14. The system of claim 13 , wherein determining that the obtained acoustic data matches stored acoustic data for the user comprises determining that stored acoustic data for the at least some of the identified subwords in the verification phrase match obtained acoustic data that correspond to the at least some of the identified subwords in the verification phrase.

15. The system of claim 14 , wherein obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase comprises obtaining a candidate phrase that includes at least one candidate subword for which stored acoustic data is associated with the user and at least one candidate subword for which no stored acoustic data is associated with the user.

16. The system of claim 15 , wherein the operations further comprise storing acoustic data from the obtained acoustic data that corresponds to the identified candidate subwords, for which no stored acoustic data is associated with the user, in association with the user.

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

receiving a request for a verification phrase for verifying an identity of a user;

in response to receiving the request for the verification phrase for verifying the identity of the user, identifying subwords to be included in the verification phrase;

in response to identifying the subwords to be included in the verification phrase, obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase, based on a predetermined criteria; and

providing the verification phrase as a response to the request for the verification phrase for verifying the identity of the user,

wherein identifying subwords to be included in the verification phrase comprises identifying candidate subwords, for which no stored acoustic data is associated with the user, as one or more of the subwords to be included in the verification phrase.

18. The computer-readable storage medium of claim 17 , wherein identifying subwords to be included in the verification phrase comprises identifying candidate subwords, for which stored acoustic data is associated with the user, as one or more of the subwords to be included in the verification phrase.

19. The computer-readable storage medium of claim 17 , wherein obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase comprises:

determining that a particular identified subword is particularly sound discriminative; and

in response to determining that the particular identified subword is particularly sound discriminative, obtaining a candidate phrase that includes the particular identified subword that is determined to be particularly sound discriminative.

20. The computer-readable storage medium of claim 17 , wherein obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase comprises:

determining that a particular identified subword is particularly sound discriminative; and

in response to determining that the particular identified subword is particularly sound discriminative, obtaining a candidate phrase that includes the particular identified subword that is determined to be particularly sound discriminative.

21. The computer-readable storage medium of claim 17 , wherein obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase comprises:

obtaining multiple candidate phrases including the candidate that includes at least some of the identified subwords;

determining that the candidate phrase includes at least some of the identified subwords; and

in response to determining that the candidate phrase includes at least some of the identified subwords, selecting the determined candidate phrase as the candidate phrase that includes at least some of the identified subwords from among the multiple candidate phrases.

22. The computer-readable storage medium of claim 17 , wherein the operations further comprise:

obtaining acoustic data representing the user speaking the verification phrase;

determining that the obtained acoustic data matches stored acoustic data for the user; and

in response to determining that the obtained acoustic data matches stored acoustic data for the user, classifying the user as the user.

23. The computer-readable storage medium of claim 22 , wherein determining that the obtained acoustic data matches stored acoustic data for the user comprises determining that stored acoustic data for the at least some of the identified subwords in the verification phrase match obtained acoustic data that correspond to the at least some of the identified subwords in the verification phrase.

24. The computer-readable storage medium of claim 23 , wherein obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase comprises obtaining a candidate phrase that includes at least one candidate subword for which stored acoustic data is associated with the user and at least one candidate subword for which no stored acoustic data is associated with the user.

25. The computer-readable storage medium of claim 24 , wherein the operations further comprise storing acoustic data from the obtained acoustic data that corresponds to the identified candidate subwords, for which no stored acoustic data is associated with the user, in association with the user.