System, method and computer program product for reduced data collection in a speech recognition tuning process

• US 20020169613A1
• Filed: 03/09/2001
• Published: 11/14/2002
• Est. Priority Date: 03/09/2001
• Status: Abandoned Application

• Current Assignee: Bevocal Incorporated (Microsoft Corporation)
• Original Assignee: Bevocal Incorporated (Microsoft Corporation)
• Inventors: Damiba, Bertrand A.
• Application Number:
  US09/802,344
• Publication Number:
  US 20020169613A1
• Time in Patent Office: Days
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence

Abstract

A system, method and computer program product are provided for collecting data for use during speech recognition tuning. Initially, utterances are received from a user utilizing a network. Thereafter, it is determined whether the utterances meet predetermined criteria. Then, if the utterances meet the predetermined criteria, the utterances from the user are stored in memory. Such stored utterances may then be used during speech recognition tuning.

Claims

1. A method for collecting data for use during speech recognition tuning, comprising the steps of:

(a) receiving utterances from a user utilizing a network;

(b) determining whether the utterances meet predetermined criteria;

(c) storing the utterances from the user in memory if the utterances meet the predetermined criteria; and

(d) utilizing the stored utterances during speech recognition tuning.

2. The method as recited in claim 1, wherein the utterances meet the predetermined criteria if the utterances match at least one of a predetermined set of grammars.

3. The method as recited in claim 1, wherein the utterances meet the predetermined criteria if the user matches at least one of a predetermined set of users.

4. The method as recited in claim 1, wherein the utterances are recognized for providing the user with a service.

5. The method as recited in claim 4, wherein the utterances meet the predetermined criteria if the service for which the utterances are recognized matches at least one of a predetermined set of services.

6. The method as recited in claim 1, wherein the network includes the Internet.

7. A computer program product for collecting data for use during speech recognition tuning, comprising:

(a) computer code for receiving utterances from a user utilizing a network;

(b) computer code for determining whether the utterances meet predetermined criteria;

(c) computer code for storing the utterances from the user in memory if the utterances meet the predetermined criteria; and

(d) computer code for utilizing the stored utterances during speech recognition.

8. The computer program product as recited in claim 7, wherein the utterances meet the predetermined criteria if the utterances match at least one of a predetermined set of grammars.

9. The computer program product as recited in claim 7, wherein the utterances meet the predetermined criteria if the user matches at least one of a predetermined set of users.

10. The computer program product as recited in claim 7, wherein the utterances are recognized for providing the user with a service.

11. The computer program product as recited in claim 10, wherein the utterances meet the predetermined criteria if the service for which the utterances are recognized matches at least one of a predetermined set of services.

12. The computer program product as recited in claim 7, wherein the network includes the Internet.

14. The system as recited in claim 13, wherein the utterances meet the predetermined criteria if the utterances match at least one of a predetermined set of grammars.

15. The system as recited in claim 13, wherein the utterances meet the predetermined criteria if the user matches at least one of a predetermined set of users.

16. The system as recited in claim 13, wherein the utterances are recognized for providing the user with a service.

17. The system as recited in claim 16, wherein the utterances meet the predetermined criteria if the service for which the utterances are recognized matches at least one of a predetermined set of services.

18. The system as recited in claim 13, wherein the network includes the Internet.

13. A system for collecting data for use during speech recognition tuning, comprising:

(a) logic for receiving utterances from a user utilizing a network;

(b) logic for determining whether the utterances meet predetermined criteria;

(c) logic for storing the utterances from the user in memory if the utterances meet the predetermined criteria; and

(d) logic for utilizing the stored utterances during speech recognition tuning.