System and method for speech personalization by need

• US 9,002,713 B2
• Filed: 06/09/2009
• Issued: 04/07/2015
• 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: Ljolje, Andrej, Conkie, Alistair D., Syrdal, Ann K.
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US12/480,864
• Publication Number:
  US 20100312556A1
• Time in Patent Office: 2,128 Days
• Field of Search: 704/270, 704/270.1, 704/275, 704/231, 704/246, 379/88.01
• US Class Current: 704/275
• 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 method comprising:

recognizing speech received from a plurality of speakers to yield recognized speech for each of the speakers, wherein each speaker in the plurality of speakers interacts with a speech interface that uses a set of allocated resources comprising a first resource and a second resource that is associated with the each speaker in the plurality of speakers, and wherein the set of allocated resources comprise at least one of bandwidth and processor time;

recording metrics associated with the recognized speech for each of the plurality of speakers, wherein the metrics comprise a speech recognition confidence score, a processing speed, a dialog behavior, a request for repetition, a negative response to confirmation, and a task completion;

after recording the metrics, while recording further speech from each speaker in the plurality of speakers, modifying at least one of the first resource and the second resource commensurate with the metrics, to yield a modified set of allocated resources; and

recognizing additional speech during a conference call from an identified speaker in the plurality of speakers using the modified set of allocated resources for speakers predetermined to be frustrated and have great difficulty in a prior session.

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

3. The method of claim 2, the method further comprising recognizing speech associated with the identified speaker based on the speaker personalization profile.

4. The method of claim 2, the method further comprising storing the speaker personalization profile on a personalization server storing multiple speaker personalization profiles.

5. The method of claim 2, wherein multiple speakers are associated with the speaker personalization profile.

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

7. The method of claim 1, wherein modifying at least one of the first resource and second resource is based on a difficulty threshold associated with how well the speaker interacts with the speech interface.

8. The method of claim 1, further comprising progressively applying the modified set of allocated resources.

9. The method of claim 1, wherein the first resource and the second resource each comprise at least one of memory and storage.

10. The method of claim 1, wherein an allocation in the modified set of allocated resources is greater than its corresponding allocation in the set of allocated resources.

11. The method of claim 1, wherein an allocation in the modified set of allocated resources is less than its corresponding allocation in the set of allocated resources.

12. 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;

recognizing speech received from a plurality of speakers to yield recognized speech for each of the speakers, wherein each speaker in the plurality of speakers interacts with a speech interface that uses a set of allocated resources comprising a first resource and a second resource that is associated with the each speaker in the plurality of speakers, and wherein the set of allocated resources comprise at least one of bandwidth and processor time;

recording metrics associated with the recognized speech for each of the plurality of speakers, wherein the metrics comprise a speech recognition confidence score, a processing speed, a dialog behavior, a request for repetition, a negative response to confirmation, and a task completion;

after recording the metrics, while recording further speech from each speaker in the plurality of speakers, modifying at least one of the first resource and the second resource commensurate with the metrics, to yield a modified set of allocated resources; and

recognizing additional speech during a conference call from an identified speaker in the plurality of speakers using the modified set of allocated resources for speakers predetermined to be frustrated and have great difficulty in a prior session.

13. The system of claim 12, the computer-readable storage medium having additional instructions stored which, when executed by the processor, result in operations comprising storing a speaker personalization profile having information for the modified set of allocated resources.

14. The system of claim 13, the computer-readable storage medium having additional instructions stored which, when executed by the processor, result in operations comprising recognizing speech associated with the identified speaker based on the speaker personalization profile.

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

recognizing speech received from a plurality of speakers to yield recognized speech for each of the speakers, wherein each speaker in the plurality of speakers interacts with a speech interface that uses a set of allocated resources comprising a first resource and a second resource that is associated with the each speaker in the plurality of speakers, and wherein the set of allocated resources comprise at least one of bandwidth and processor time;

recording metrics associated with the recognized speech for each of the plurality of speakers, wherein the metrics comprise a speech recognition confidence score, a processing speed, a dialog behavior, a request for repetition, a negative response to confirmation, and a task completion;

after recording the metrics, while recording further speech from each speaker in the plurality of speakers, modifying at least one of the first resource and the second resource commensurate with the metrics, to yield a modified set of allocated resources;

recognizing additional speech during a conference call from an identified speaker in the plurality of speakers using the modified set of allocated resources for speakers predetermined to be frustrated and have great difficulty in a prior session.

16. The computer-readable storage device of claim 15, having additional instructions stored which, when executed by the computing device, result in operations comprising progressively applying the modified set of allocated resources.

17. The computer-readable storage device of claim 15, wherein the first resource and the second resource each further comprise at least one of memory and storage.

18. The computer-readable storage device of claim 15, wherein an allocation in the modified set of allocated resources is greater than its corresponding allocation in the set of allocated resources.