Method and Apparatus for Performing Speaker Recognition

• US 20160086607A1
• Filed: 09/18/2014
• Published: 03/24/2016
• Est. Priority Date: 09/18/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Farrell, Kevin R., Aley-Raz, Almog, Yaron, Oshrit, Scarpato, Luca
• Granted Patent: US 10,008,208 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 17/06 Decision making techniques; Pattern matching strategies
• 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 17/24 the user being prompted to utter a password or a predefined phrase

Abstract

Embodiments of the present invention perform speaker identification and verification by first prompting a user to speak a phrase that includes a common phrase component and a personal identifier. Then, the embodiments decompose the spoken phrase to locate the personal identifier. Finally, the embodiments identify and verify the user based on the results of the decomposing.

Claims

1. A method of performing speaker recognition, the method comprising:

prompting a user to speak a phrase including a personal identifier and a common phrase component;

decomposing a received spoken phrase, the decomposing including locating the personal identifier within the spoken phrase; and

identifying and verifying the user based on results of the decomposing.

2. The method of claim 1 wherein identifying the user comprises:

comparing the personal identifier against previously stored identifying information.

3. The method of claim 1 wherein the decomposing further includes:

locating the common phrase component, the common phrase component being a component of the spoken phrase common amongst users within at least a subgroup of all users.

4. The method of claim 3 wherein verifying the user comprises:

comparing the common phrase component against one or more previously stored voice prints associated with at least the subgroup of all users.

5. The method of claim 3 wherein the common phrase component of the spoken phrase comprises two or more phrases and the verifying further includes:

calculating a respective score for each phrase of the common phrase component, the respective scores indicating a level of correspondence between the two or more phrases and one or more stored voice prints; and

verifying the user using the respective scores.

6. The method of claim 5 wherein verifying the user using the respective scores comprises:

averaging the respective scores; and

comparing the average against a predetermined threshold.

7. The method claim 1 wherein verifying the user further comprises:

determining a score indicating a level of correspondence between the received spoken phrase and one or more stored voice prints; and

verifying the user when the score is greater than a predetermined threshold.

8. The method of claim 1 wherein decomposing the received spoken phrase utilizes key word spotting.

9. The method of claim 1 wherein identifying the user comprises:

determining multiple candidate users associated with the personal identifier; and

employing voice biometrics to identify the user among the multiple candidate users.

10. The method of claim 9 wherein employing voice biometrics includes:

comparing the common phrase component of the spoken phrase or the received spoken phrase against corresponding previously stored voice prints for each candidate user.

11. A computer system for performing speaker recognition, the computer system comprising:

a processor; and

a memory with computer code instructions stored thereon, the processor and the memory, with the computer code instructions being configured to cause the system to;

prompt a user to speak a phrase including a personal identifier and a common phrase component;

decompose a received spoken phrase, the decomposing including locating the personal identifier within the spoken phrase; and

identify and verify the user based on results of the decomposing.

12. The computer system of claim 11, wherein, in identifying the user, the processor and the memory, with the computer code instructions, are further configured to cause the system to:

compare the personal identifier against previously stored identifying information.

13. The computer system of claim 11, wherein, in decomposing the received spoken phrase, the processor and the memory, with the computer code instructions, are further configured to cause the system to:

locate the common phrase component, the common phrase component being a component of the spoken phrase common amongst users within at least a subgroup of all users.

14. The computer system of claim 13, wherein, in verifying the user, the processor and the memory, with the computer code instructions, are further configured to cause the system to:

compare the common phrase component against one or more previously stored voice prints associated with at least the subgroup of all users.

15. The computer system of claim 13 wherein the common phrase component of the spoken phrase comprises two or more phrases and wherein, in the verifying, the processor and the memory, with the computer code instructions, are further configured to cause the system to:

calculate a respective score for each phrase of the common phrase component, the respective scores indicating a level of correspondence between the two or more phrases and one or more stored voice prints; and

verifying the user using the respective scores.

16. The computer system of claim 11 wherein, in verifying the user, the processor and the memory, with the computer code instructions, are further configured to cause the system to:

determine a score indicating a level of correspondence between the received spoken phrase and one or more stored voice prints; and

verify the user when the score is greater than a predetermined threshold.

17. The computer system of claim 11 wherein, in decomposing the received spoken phrase, the processor and the memory, with the computer code instructions, are further configured to cause the system to utilize key word spotting.

18. The computer system of claim 11 wherein, in identifying the user, the processor and the memory, with the computer code instructions, are further configured to cause the system to:

determine multiple candidate users associated with the personal identifier; and

employ voice biometrics to identify the user among the multiple candidate users.

19. The computer system of claim 18 wherein, in employing voice biometrics, the processor and the memory, with the computer code instructions, are further configured to cause the system to:

compare the common phrase component of the spoken phrase or the received spoken phrase against corresponding previously stored voice prints for each candidate user.

20. A computer program product for performing speaker verification, the computer program product comprising:

one or more computer-readable tangible storage devices and program instructions stored on at least one of the one or more storage devices, the program instructions, when loaded and executed by a processor, cause an apparatus associated with the processor to;

prompt a user to speak a phrase including a personal identifier and a common phrase component;

decompose a received spoken phrase, the decomposing including locating the personal identifier within the spoken phrase; and

identify and verify the user based on results of the decomposing.