System and method for detecting synthetic speaker verification

• US 8,504,365 B2
• Filed: 04/11/2008
• Issued: 08/06/2013
• 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
• Primary Examiner(s): COLUCCI, MICHAEL C
• Application Number:
  US12/101,482
• Publication Number:
  US 20090259468A1
• Time in Patent Office: 1,943 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: 704/246
• 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 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;

receiving speech from the user, distinct from the plurality of stored speech samples, to be verified;

receiving a parameter that identifies a certainty level associated with the variance, from a plurality of certainty levels, to be applied when verifying the speech as authentic;

based on the certainty level, verifying the speech as authentic, to yield a verification; and

transmitting access data based on the verification.

2. The method of claim 1, wherein each of the plurality of speech samples is collected in one of a different time and in a different context.

3. The method of claim 1, wherein the certainty level is based on a predetermined threshold.

4. The method of claim 1, wherein each certainty level of the plurality of certainty levels is associated with a different task.

5. The method of claim 1, wherein each certainty level of the plurality of certainty levels is associated with a different user.

6. A system comprising:

a processor;

a computer-readable storage medium having instructions stored for controlling the processor to perform operations comprising;

receiving 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;

receiving speech from the user, distinct from the plurality of stored speech samples, to be verified;

receiving a parameter that identifies a certainty level associated with the variance, from a plurality of certainty levels, to be applied when verifying the speech as authentic;

based on the certainty level, verifying the speech as authentic, to yield a verification; and

transmitting access data based on the verification.

7. The system of claim 6, wherein each of the plurality of speech samples is collected in one of a different time and in a different context.

8. The system of claim 6, wherein the certainty level is based on a predetermined threshold.

9. The system of claim 6, wherein each certainty level of the plurality of certainty levels is associated with a different task.

10. The system of claim 6, wherein each certainty level of the plurality of certainty levels is associated with a different user.

11. A computer-readable storage device having instructions stored for controlling a computing device to perform operations comprising:

receiving 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;

receiving speech from the user, distinct from the plurality of stored speech samples, to be verified;

receiving a parameter that identifies a certainty level associated with the variance, from a plurality of certainty levels, to be applied when verifying the speech as authentic;

based on the certainty level, verifying the speech as authentic, to yield a verification; and

transmitting access data based on the verification.

12. The computer-readable storage device of claim 11, wherein each of the plurality of speech samples is collected in one of a different time and in a different context.

13. The computer-readable storage device of claim 11, wherein the certainty level is based on a predetermined threshold.

14. The computer-readable storage device of claim 11, wherein each certainty level of the plurality of certainty levels is associated with a different task.

15. The computer-readable storage device of claim 11, wherein each certainty level of the plurality of certainty levels is associated with a different user.