SYSTEM AND METHOD FOR SPEECH PERSONALIZATION BY NEED

• US 20100312556A1
• Filed: 06/09/2009
• Published: 12/09/2010
• Est. Priority Date: 06/09/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: CONKIE, Alistair D., LJOLJE, Andrej, SYRDAL, Ann K.
• Granted Patent: US 9,002,713 B2
• Time in Patent Office: Days
• US Class Current: 704/244
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Disclosed herein are systems, computer-implemented methods, and tangible computer-readable storage media for speaker recognition personalization. The method recognizes speech received from a speaker interacting with a speech interface using a set of allocated resources, the set of allocated resources including bandwidth, processor time, memory, and storage. The method records metrics associated with the recognized speech, and after recording the metrics, modifies at least one of the allocated resources in the set of allocated resources commensurate with the recorded metrics. The method recognizes additional speech from the speaker using the modified set of allocated resources. Metrics can include a speech recognition confidence score, processing speed, dialog behavior, requests for repeats, negative responses to confirmations, and task completions. The method can further store a speaker personalization profile having information for the modified set of allocated resources and recognize speech associated with the speaker based on the speaker personalization profile.

Claims

1. A computer-implemented method of speaker recognition personalization, the method comprising:

recognizing speech received from a speaker interacting with a speech interface using a set of allocated resources, the set of allocated resources comprising bandwidth, processor time, memory, and storage;

recording metrics associated with the recognized speech;

after recording the metrics, modifying at least one of the allocated resources in the set of allocated resources commensurate with the recorded metrics; and

recognizing additional speech from the speaker using the modified set of allocated resources.

2. The computer-implemented method of claim 1, wherein the metrics comprise at least one of speech recognition confidence score, processing speed, dialog behavior, requests for repeats, negative responses to confirmations, and task completions.

3. The computer-implemented method of claim 1, the method further comprising storing a speaker personalization profile having information for the modified set of allocated resources.

4. The computer-implemented method of claim 3, the method further comprising recognizing speech associated with the speaker based on the speaker personalization profile.

5. The computer-implemented method of claim 3, the method further comprising storing the speaker personalization profile on a personalization server storing multiple speaker personalization profiles.

6. The computer-implemented method of claim 3, wherein multiple speakers are associated with the speaker personalization profile.

7. The computer-implemented method of claim 1, wherein the modified set of allocated resources is associated with a class of similar speakers.

8. The computer-implemented method of claim 1, wherein modifying at least one of the allocated resources is based on a difficulty threshold associated with how well the speaker interacts with the speech interface.

9. The computer-implemented method of claim 1, the method further comprising progressively applying the modified set of allocated resources.

10. The computer-implemented method of claim 1, the method further comprising, while recognizing the additional speech from the speaker, transitioning between the set of allocated resources and the modified set of allocated resources.

11. The computer-implemented method of claim 1, wherein at least one allocation in the modified set of allocated resources is greater than its corresponding allocation in the set of allocated resources.

12. The computer-implemented method of claim 1, wherein at least one allocation in the modified set of allocated resources is less than its corresponding allocation in the set of allocated resources.

13. A system for speaker recognition personalization, the system comprising:

a processor;

a first recognition module configured to control the processor to recognize speech received from a speaker interacting with a speech interface using a set of allocated resources, the set of allocated resources comprising bandwidth, processor time, memory, and storage;

a recording module configured to control the processor to record metrics associated with the recognized speech;

a modification module configured to control the processor to, after recording the metrics, modify at least one of the allocated resources in the set of allocated resources commensurate with the recorded metrics; and

a second recognition module configured to control the processor to recognize additional speech from the speaker using the modified set of allocated resources.

14. The system of claim 13, wherein the metrics comprise at least one of speech recognition confidence score, processing speed, dialog behavior, requests for repeats, negative responses to confirmations, and task completions.

15. The system of claim 13, the system further comprising a speaker personalization storage module configured to control the processor to store a speaker personalization profile having information for the modified set of allocated resources.

16. The system of claim 15, the system further comprising a speaker personalization profile module configured to control the processor to recognize speech associated with the speaker based on the speaker personalization profile.

17. A tangible computer-readable medium storing a computer program having instructions for speaker recognition personalization, the instructions comprising:

recognizing speech received from a speaker interacting with a speech interface using a set of allocated resources, the set of allocated resources comprising bandwidth, processor time, memory, and storage;

recording metrics associated with the recognized speech;

after recording the metrics, modifying at least one of the allocated resources in the set of allocated resources commensurate with the recorded metrics; and

recognizing additional speech from the speaker using the modified set of allocated resources.

18. The tangible computer-readable medium of claim 17, the method further comprising progressively applying the modified set of allocated resources.

19. The tangible computer-readable medium of claim 17, the method further comprising, while recognizing the additional speech from the speaker, transitioning between the set of allocated resources and the modified set of allocated resources.

20. The tangible computer-readable medium of claim 17, wherein at least one allocation in the modified set of allocated resources is greater than its corresponding allocation in the set of allocated resources.