System and method for detecting synthetic speaker verification

• US 9,142,218 B2
• Filed: 08/07/2014
• Issued: 09/22/2015
• Est. Priority Date: 04/11/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Schroeter, Horst J.
• Primary Examiner(s): COLUCCI, MICHAEL C
• Application Number:
  US14/454,104
• Publication Number:
  US 20140350938A1
• Time in Patent Office: 411 Days
• Field of Search: 704/250, 704/273, 704/275, 704/271, 704/252, 704/248, 704/247, 704/246, 704/243, 704/223, 704/219, 704/208, 455/563, 379/361, 340/5.52, 713/169
• US Class Current: 1/1
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 17/08 Use of distortion metrics or a particular distance between probe pattern and reference templates
• CPC Class Codes: G10L 17/20 Pattern transformations or operations aimed at increasing system robustness, e.g. against channel noise or different working conditions
• CPC Class Codes: G10L 17/24 the user being prompted to utter a password or a predefined phrase

Abstract

Disclosed herein are systems, methods, and tangible computer readable-media for detecting synthetic speaker verification. The method comprises receiving a plurality of speech samples of the same word or phrase for verification, comparing each of the plurality of speech samples to each other, denying verification if the plurality of speech samples demonstrate little variance over time or are the same, and verifying the plurality of speech samples if the plurality of speech samples demonstrates sufficient variance over time. One embodiment further adds that each of the plurality of speech samples is collected at different times or in different contexts. In other embodiments, variance is based on a pre-determined threshold or the threshold for variance is adjusted based on a need for authentication certainty. In another embodiment, if the initial comparison is inconclusive, additional speech samples are received.

Claims

1. A method comprising:

receiving, from a database, a plurality of stored speech samples of a same word for verifying a user;

comparing, via a processor, each of the plurality of stored speech samples to each other, to yield a variance over time; and

verifying speech received from the user as authentic based on the variance over time.

2. The method of claim 1, further comprising

transmitting access data based on the verifying of the speech as authentic.

3. The method of claim 2, wherein the access data provides access to a restricted location.

4. The method of claim 2, wherein the access data unlocks a cellphone.

5. The method of claim 1, wherein each of the plurality of speech samples is collected in a different context.

6. The method of claim 1, further comprising prompting the user to say the same word.

7. The method of claim 1, wherein the plurality of stored samples is collected during an enrollment period.

8. A system comprising:

a processor; and

a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising;

receiving, from a database, a plurality of stored speech samples of a same word for verifying a user;

comparing each of the plurality of stored speech samples to each other, to yield a variance over time; and

verifying speech received from the user as authentic based on the variance over time.

9. The system of claim 8, the computer-readable storage medium having additional instructions stored which result in operations comprising

transmitting access data based on the verifying of the speech as authentic.

10. The system of claim 9, wherein the access data provides access to a restricted location.

11. The system of claim 9, wherein the access data unlocks a cellphone.

12. The system of claim 8, wherein each of the plurality of speech samples is collected in a different context.

13. The system of claim 8, the computer-readable storage medium having additional instructions stored which result in operations comprising prompting the user to say the same word.

14. The system of claim 8, wherein the plurality of stored samples is collected during an enrollment period.

15. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:

receiving, from a database, a plurality of stored speech samples of a same word for verifying a user;

comparing each of the plurality of stored speech samples to each other, to yield a variance over time; and

verifying speech received from the user as authentic based on the variance over time.

16. The computer-readable storage device of claim 15, having additional instructions stored which result in operations comprising

transmitting access data based on the verifying of the speech as authentic.

17. The computer-readable storage device of claim 16, wherein the access data provides access to a restricted location.

18. The computer-readable storage device of claim 16, wherein the access data unlocks a cellphone.

19. The computer-readable storage device of claim 15, wherein each of the plurality of speech samples is collected in a different context.

20. The computer-readable storage device of claim 15, having additional instructions stored which result in operations comprising prompting the user to say the same word.