Dynamic threshold for speaker verification

• US 9,972,323 B2
• Filed: 05/19/2017
• Issued: 05/15/2018
• Est. Priority Date: 06/24/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Foerster, Jakob Nicolaus, Melendo Casado, Diego
• Primary Examiner(s): Baker, Charlotte M
• Application Number:
  US15/599,578
• Publication Number:
  US 20170345430A1
• Time in Patent Office: 361 Days
• Field of Search: 704250, 715735, 715741, 715743
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/02 Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• CPC Class Codes: G10L 17/08 Use of distortion metrics or a particular distance between probe pattern and reference templates
• CPC Class Codes: G10L 17/12 Score normalisation
• CPC Class Codes: G10L 17/14 Use of phonemic categorisation or speech recognition prior to speaker recognition or verification
• CPC Class Codes: G10L 17/20 Pattern transformations or operations aimed at increasing system robustness, e.g. against channel noise or different working conditions
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 17/24 the user being prompted to utter a password or a predefined phrase
• CPC Class Codes: G10L 25/84 for discriminating voice from noise
• CPC Class Codes: H04M 3/385 using speech signals

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a dynamic threshold for speaker verification are disclosed. In one aspect, a method includes the actions of receiving, for each of multiple utterances of a hotword, a data set including at least a speaker verification confidence score, and environmental context data. The actions further include selecting from among the data sets, a subset of the data sets that are associated with a particular environmental context. The actions further include selecting a particular data set from among the subset of data sets based on one or more selection criteria. The actions further include selecting, as a speaker verification threshold for the particular environmental context, the speaker verification confidence score. The actions further include providing the speaker verification threshold for use in performing speaker verification of utterances that are associated with the particular environmental context.

Claims

1. A computer-implemented method comprising:

receiving, by a computing device that uses voice-based speaker identification, data identifying an utterance previously received by the computing device and data indicating that a user likely did speak the utterance;

prompting the user to confirm that the user did speak the utterance;

receiving, from the user, data indicating that the user has confirmed that the user did speak the utterance; and

in response to receiving the data indicating that the user has confirmed that the user did speak the utterance, using audio data corresponding to the utterance previously received by the computing device to perform voice-based speaker identification on a subsequently received utterance that has a shared characteristic with the utterance previously received, wherein the shared characteristic is (i) an amount of background noise within a same background noise range, (ii) an amount of loudness within a same loudness range, or (iii) a signal-to-noise ratio within a same signal-to-noise ratio range.

2. The method of claim 1, comprising:

recognizing an identity of the user using a technique other than voice-based speaker identification.

3. The method of claim 2, wherein recognizing the identity of the user using the technique other than voice-based speaker identification comprises prompting the user for a passcode.

4. The method of claim 1, wherein the utterance previously received by the computing device and the subsequently received utterance each include a predefined hotword.

5. The method of claim 1, wherein the amount of background noise is measured prior to receipt of the previously received utterance and the subsequently received utterance.

6. The method of claim 1, wherein prompting the user to confirm that the user did speak the utterance comprises:

providing, for display, data indicating a date and time when the utterance was received.

7. 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, by a computing device that uses voice-based speaker identification, data identifying an utterance previously received by the computing device and data indicating that a user likely did speak the utterance;

prompting the user to confirm that the user did speak the utterance;

receiving, from the user, data indicating that the user has confirmed that the user did speak the utterance; and

in response to receiving the data indicating that the user has confirmed that the user did speak the utterance, using audio data corresponding to the utterance previously received by the computing device to perform voice-based speaker identification on a subsequently received utterance that has a shared characteristic with the utterance previously received, wherein the shared characteristic is (i) an amount of background noise within a same background noise range, (ii) an amount of loudness within a same loudness range, or (iii) a signal-to-noise ratio within a same signal-to-noise ratio range.

8. The system of claim 7, wherein the operations further comprise:

recognizing an identity of the user using a technique other than voice-based speaker identification.

9. The system of claim 8, wherein recognizing the identity of the user using the technique other than voice-based speaker identification comprises prompting the user for a passcode.

10. The system of claim 7, wherein the utterance previously received by the computing device and the subsequently received utterance each include a predefined hotword.

11. The system of claim 7, wherein the amount of background noise is measured prior to receipt of the previously received utterance and the subsequently received utterance.

12. The system of claim 7, wherein prompting the user to confirm that the user did speak the utterance comprises:

providing, for display, data indicating a date and time when the utterance was received.

13. A non-transitory computer-readable 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, by a computing device that uses voice-based speaker identification, data identifying an utterance previously received by the computing device and data indicating that a user likely did speak the utterance;

prompting the user to confirm that the user did speak the utterance;

receiving, from the user, data indicating that the user has confirmed that the user did speak the utterance; and

in response to receiving the data indicating that the user has confirmed that the user did speak the utterance, using audio data corresponding to the utterance previously received by the computing device to perform voice-based speaker identification on a subsequently received utterance that has a shared characteristic with the utterance previously received, wherein the shared characteristic is (i) an amount of background noise within a same background noise range, (ii) an amount of loudness within a same loudness range, or (iii) a signal-to-noise ratio within a same signal-to-noise ratio range.

14. The medium of claim 13, wherein the utterance previously received by the computing device and the subsequently received utterance each include a predefined hotword.

15. The medium of claim 13, wherein the operations further comprise:

recognizing an identity of the user using a technique other than voice-based speaker identification.

16. The medium of claim 15, wherein recognizing the identity of the user using the technique other than voice-based speaker identification comprises prompting the user for a passcode.

17. The medium of claim 13, wherein the amount of background noise is measured prior to receipt of the previously received utterance and the subsequently received utterance.

18. The medium of claim 13, wherein prompting the user to confirm that the user did speak the utterance comprises:

providing, for display, data indicating a date and time when the utterance was received.

19. A computer-implemented method comprising:

receiving, by a computing device that uses voice-based speaker identification, data identifying an utterance previously received by the computing device and data indicating that a user likely did speak the utterance;

providing, for display, a prompt for the user to confirm that the user did speak the utterance, the prompt indicating a date and time that the utterance was received;

receiving, from the user, data indicating that the user has confirmed that the user did speak the utterance; and

in response to receiving the data indicating that the user has confirmed that the user did speak the utterance, using audio data corresponding to the utterance previously received by the computing device to perform voice-based speaker identification on a subsequently received utterance.