System and method for targeted tuning of a speech recognition system

• US 8,751,232 B2
• Filed: 02/06/2013
• Issued: 06/10/2014
• Est. Priority Date: 08/12/2004
• Status: Active Grant

• Current Assignee: Interactions, LLC
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Bushey, Robert R., Knott, Benjamin Anthony, Martin, John Mills
• Primary Examiner(s): ALBERTALLI, BRIAN LOUIS
• Application Number:
  US13/760,897
• Publication Number:
  US 20130151253A1
• Time in Patent Office: 489 Days
• Field of Search: None
• US Class Current: 704/244
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A system and method of targeted tuning of a speech recognition system are disclosed. A particular method includes detecting that a frequency of occurrence of a particular type of utterance satisfies a threshold. The method further includes tuning a speech recognition system with respect to the particular type of utterance.

Claims

1. A method comprising:

detecting that a frequency of occurrence of a particular type of utterance satisfies a threshold; and

in response to detecting that the frequency satisfies the threshold, tuning a speech recognition system with respect to the particular type of utterance.

2. The method of claim 1, further comprising determining the frequency based on a group of received utterances.

3. The method of claim 1, wherein the threshold is determined by a system administrator.

4. The method of claim 1, wherein the threshold is user programmable.

5. The method of claim 1, wherein tuning the speech recognition system includes inputting a collection of utterances of the particular type of utterance into a learning module of the speech recognition system.

6. The method of claim 5, wherein inputting the collection of utterances includes playing one or more files that represent recordings of the particular type of utterance.

7. The method of claim 1, wherein system recognition of the particular type of utterance is dependent on a particular speaker.

8. The method of claim 1, wherein system recognition of the particular type of utterance is independent of a particular speaker.

9. The method of claim 1, wherein the utterance is one of a single word spoken by a speaker, a phrase spoken by the speaker, or a sentence spoken by the speaker.

10. The method of claim 1, wherein the utterance corresponds to a request that indicates an action to be taken on an object.

11. The method of claim 10, wherein the request is one of a request to pay a bill, a request for an account balance, a request to change services, a request to acquire services, a request to cancel services, a request to schedule a payment, or a request to reconnect services.

12. A speech recognition system, comprising:

a processor; and

a tuning engine comprising instructions that are executable by the processor to tune a speech module with respect to a particular type of utterance in response to the processor determining that a frequency of occurrence of the particular type of utterance satisfies a threshold.

13. The speech recognition system of claim 12, further comprising a targeting engine including instructions that are executable by the processor to:

determine the frequency of occurrence of the particular type of utterance; and

determine that the frequency of occurrence of the particular type of utterance satisfies the threshold.

14. The speech recognition system of claim 12, wherein the threshold is from a table of thresholds, the thresholds corresponding to a plurality of utterance types.

15. The speech recognition system of claim 12, further comprising an accuracy engine including instructions executable by the processor to determine an accuracy of recognition of the particular type of utterance.

16. The speech recognition system of claim 15, wherein the accuracy of recognition of the particular type of utterance is compared to an accuracy threshold.

17. The speech recognition system of claim 16, wherein the tuning engine is responsive to the accuracy engine.

18. The speech recognition system of claim 15, wherein the frequency of occurrence of the particular type of utterance depends on the accuracy of recognition of the particular type of utterance.

19. A computer readable storage device comprising instructions that, when executed by a processor, cause the processor to perform operations comprising:

detecting that a frequency of occurrence of a particular type of utterance satisfies a threshold; and

in response to detecting that the frequency satisfies the threshold, tuning a speech recognition system with respect to the particular type of utterance.

20. The computer readable storage device of claim 19, wherein the operations further include:

calculating a hit rate associated with the particular type of utterance;

calculating a false alarm value associated with the particular type of utterance; and

maintaining a record of performance of the speech recognition system.