SYSTEM AND METHOD FOR VOICE AUTHENTICATION

• US 20100145709A1
• Filed: 12/04/2008
• Published: 06/10/2010
• Est. Priority Date: 12/04/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Kumar, Saurabh
• Granted Patent: US 8,095,368 B2
• Time in Patent Office: Days
• US Class Current: 704/273
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• 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: H04L 63/0861 using biometrical features, e.g. fingerprint, retina-scan cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231
• CPC Class Codes: H04L 63/10 for controlling access to devices or network resources

Abstract

Disclosed herein are systems, computer-implemented methods, and tangible computer-readable media for voice authentication. The method includes receiving a speech sample from a user through an Internet browser for authentication as part of a request for a restricted-access resource, performing a comparison of the received speech sample to a previously established speech profile associated with the user, transmitting an authentication to the network client if the comparison is equal to or greater than a certainty threshold, and transmitting a denial to the network client if the comparison is less than the certainty threshold.

Claims

1. A computer-implemented method of voice authentication, the method comprising:

receiving a speech sample from a user through an Internet browser for authentication as part of a request for a restricted-access resource;

performing a comparison of the received speech sample to a previously established speech profile associated with the user;

transmitting an authentication to the network client if the comparison is equal to or greater than a certainty threshold; and

transmitting a denial to the network client if the comparison is less than the certainty threshold.

2. The computer-implemented method of claim 1, wherein the user captures and sends the speech sample with a single user input.

3. The computer-implemented method of claim 1, wherein a computing device running the Internet browser preauthenticates the received speech sample before sending the speech sample to the server.

4. The computer-implemented method of claim 3, wherein the computing device preauthentication is more relaxed than the server authentication.

5. The computer-implemented method of claim 3, wherein a decision to preauthenticate is based on network conditions.

6. The computer-implemented method of claim 1, wherein a received user token must match a previously established user token before transmitting the authentication to the network client.

7. The computer-implemented method of claim 1, the method further comprising:

sending to the user with a prompt for an additional speech sample due to feigned poor speech recognition if the comparison is less than the certainty threshold;

receiving the additional speech sample from the user;

performing a second comparison of the additional received speech sample to the previously established speech profile associated with the user; and

transmitting an authentication to the network client if the second comparison is equal to or greater than a certainty threshold.

8. The computer-implemented method of claim 1, wherein the received speech sample is a password.

9. The computer-implemented method of claim 1, wherein the user reads specified text to generate the speech sample.

10. A system for voice authentication, the system comprising:

a module configured to receive a speech sample from a user through an Internet browser for authentication as part of a request for a restricted-access resource;

a module configured to perform a comparison of the received speech sample to a previously established speech profile associated with the user;

a module configured to transmit an authentication to the network client if the comparison is equal to or greater than a certainty threshold; and

a module configured to transmit a denial to the network client if the comparison is less than the certainty threshold.

11. The system of claim 10, wherein the user captures and sends the speech sample with a single user input.

12. The system of claim 10, wherein a computing device running the Internet browser preauthenticates the received speech sample before sending the speech sample to the server.

13. The system of claim 10, wherein a received user token must match a previously established user token before transmitting the authentication to the network client.

14. The system of claim 10, the system further comprising:

a module configured to send to the user with a prompt for an additional speech sample due to feigned poor speech recognition if the comparison is less than the certainty threshold;

a module configured to receive the additional speech sample from the user;

a module configured to perform a second comparison of the additional received speech sample to the previously established speech profile associated with the user; and

a module configured to transmit an authentication to the network client if the second comparison is equal to or greater than a certainty threshold.

15. A tangible computer-readable medium storing a computer program having instructions for voice authentication, the instructions comprising:

receiving a speech sample from a user through an Internet browser for authentication as part of a request for a restricted-access resource;

performing a comparison of the received speech sample to a previously established speech profile associated with the user;

transmitting an authentication to the network client if the comparison is equal to or greater than a certainty threshold; and

transmitting a denial to the network client if the comparison is less than the certainty threshold.

16. The tangible computer-readable medium of claim 15, wherein the user captures and sends the speech sample with a single user input.

17. The tangible computer-readable medium of claim 15, wherein a computing device running the Internet browser preauthenticates the received speech sample before sending the speech sample to the server.

18. The tangible computer-readable medium of claim 17, wherein the computing device preauthentication is more relaxed than the server authentication.

19. The tangible computer-readable medium of claim 17, wherein a decision to preauthenticate is based on network conditions.

20. The tangible computer-readable medium of claim 15, the instructions further comprising:

sending to the user with a prompt for an additional speech sample due to feigned poor speech recognition if the comparison is less than the certainty threshold;

receiving the additional speech sample from the user;

performing a second comparison of the additional received speech sample to the previously established speech profile associated with the user; and

transmitting an authentication to the network client if the second comparison is equal to or greater than a certainty threshold.