AUTOMATED TUNING OF SPEECH RECOGNITION PARAMETERS

• US 20090106028A1
• Filed: 10/18/2007
• Published: 04/23/2009
• Est. Priority Date: 10/18/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Mandalia, Baiju D., Nusbickel, Wendi L., Dhanakshirur, Girish
• Granted Patent: US 9,129,599 B2
• Time in Patent Office: Days
• US Class Current: 704/270.100
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• 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
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method for execution on a server for serving presence information, the method for providing dynamically loaded speech recognition parameters to a speech recognition engine, can be provided. The method can include storing at least one rule for selecting speech recognition parameters, wherein a rule comprises an if-portion including criteria and a then-portion specifying speech recognition parameters that must be used when the criteria is met. The method can further include receiving notice that a speech recognition session has been initiated between a user and the speech recognition engine. The method can further include selecting a first set of speech recognition parameters responsive to executing the at least one rule and providing to the speech recognition engine the first set of speech recognition parameters for performing speech recognition of the user.

Claims

1. A method for execution on a server for serving presence information, the method for providing dynamically loaded speech recognition parameters to a speech recognition engine, comprising:

storing at least one rule for selecting speech recognition parameters, wherein a rule comprises an if-portion including criteria and a then-portion specifying speech recognition parameters that must be used when the criteria is met;

receiving notice that a speech recognition session has been initiated between a user and the speech recognition engine;

executing the at least one rule;

selecting a first set of speech recognition parameters responsive to executing the at least one rule; and

providing to the speech recognition engine the first set of speech recognition parameters for performing speech recognition of the user.

2. The method of claim 1, wherein the step of storing at least one rule comprises:

storing at least one rule for selecting speech recognition parameters, wherein a rule comprises an if-portion including criteria and a then-portion specifying speech recognition parameters that must be used when the criteria is met, and wherein criteria includes at least one value for at least one of time of day, recognition accuracy of the speech recognition engine, and grammar usage of the speech recognition engine.

3. The method of claim 2, wherein the step of storing at least one rule further comprises:

storing at least one rule for selecting speech recognition parameters, wherein a rule comprises an if-portion including criteria and a then-portion specifying speech recognition parameters that must be used when the criteria is met, and wherein speech recognition parameters include any one of grammars, weights, accuracy settings, thresholds, and sensitivity.

4. The method of claim 3, wherein the step of executing the at least one rule comprises:

reading metadata including at least one value for at least one of time of day, recognition accuracy of the speech recognition engine, and grammar usage of the speech recognition engine; and

determining that the metadata meets criteria of the at least one rule.

5. The method of claim 4, wherein the step of selecting a first set of speech recognition parameters comprises:

selecting a first set of speech recognition parameters identical to the speech recognition parameters specified by the then-portion of the at least one rule.

6. A method for execution on a server for serving presence information, the method for providing dynamically loaded speech recognition parameters to a speech recognition engine, comprising:

storing at least one rule for selecting speech recognition parameters, wherein a rule comprises an if-portion including criteria and a then-portion specifying speech recognition parameters that must be used when the criteria is met;

storing periodically updated metadata about a plurality of speech recognition engines;

selecting a first speech recognition engine based on most recently stored metadata;

receiving notice that a speech recognition session has been initiated between a user and the first speech recognition engine;

executing the at least one rule;

selecting a first set of speech recognition parameters responsive to executing the at least one rule; and

providing to the first speech recognition engine the first set of speech recognition parameters for performing speech recognition of the user.

7. The method of claim 6, wherein the step of storing at least one rule comprises:

storing at least one rule for selecting speech recognition parameters, wherein a rule comprises an if-portion including criteria and a then-portion specifying speech recognition parameters that must be used when the criteria is met, and wherein criteria includes at least one value for at least one of time of day, recognition accuracy of a speech recognition engine, and grammar usage of a speech recognition engine.

8. The method of claim 7, wherein the step of storing at least one rule further comprises:

storing at least one rule for selecting speech recognition parameters, wherein a rule comprises an if-portion including criteria and a then-portion specifying speech recognition parameters that must be used when the criteria is met, and wherein speech recognition parameters include any one of grammars, weights, accuracy settings, thresholds, and sensitivity.

9. The method of claim 8, wherein the step of storing periodically updated metadata comprises:

storing periodically updated metadata about a plurality of speech recognition engines, including any one of load data, supported grammars, availability, health, supported languages and acoustic model characteristics.

10. The method of claim 9, wherein the step of executing the at least one rule comprises:

reading metadata including at least one value for at least one of time of day, recognition accuracy of the first speech recognition engine, and grammar usage of the first speech recognition engine; and

determining that the metadata meets criteria of the at least one rule.

11. The method of claim 10, wherein the step of selecting a first set of speech recognition parameters comprises:

selecting a first set of speech recognition parameters identical to the speech recognition parameters specified by the then-portion of the at least one rule.

12. A computer system comprising a server for serving presence information, the server for providing dynamically loaded speech recognition parameters to a speech recognition engine, comprising:

a repository for storing at least one rule for selecting speech recognition parameters, wherein a rule comprises an if-portion including criteria and a then-portion specifying speech recognition parameters that must be used when the criteria is met; and

a processor configured for;

receiving notice that a speech recognition session has been initiated between a user and the speech recognition engine;

executing the at least one rule;

selecting a first set of speech recognition parameters responsive to executing the at least one rule; and

providing to the speech recognition engine the first set of speech recognition parameters for performing speech recognition of the user.

13. The computer system of claim 12, wherein criteria includes at least one value for at least one of time of day, recognition accuracy of the speech recognition engine, and grammar usage of the speech recognition engine.

14. The computer system of claim 13, wherein speech recognition parameters include any one of grammars, weights, accuracy settings, thresholds, and sensitivity.

15. The computer system of claim 12, further comprising:

a load balancing server for distributing speech recognition sessions among a plurality of speech recognition engines based on availability of the speech recognition engines.

16. A computer program product comprising a computer usable medium on a server for serving presence information, the computer usable medium embodying computer usable program code for providing dynamically loaded speech recognition parameters to a speech recognition engine, comprising:

computer usable program code for storing at least one rule for selecting speech recognition parameters, wherein a rule comprises an if-portion including criteria and a then-portion specifying speech recognition parameters that must be used when the criteria is met;

computer usable program code for receiving notice that a speech recognition session has been initiated between a user and the speech recognition engine;

computer usable program code for executing the at least one rule;

computer usable program code for selecting a first set of speech recognition parameters responsive to executing the at least one rule; and

computer usable program code for providing to the speech recognition engine the first set of speech recognition parameters for performing speech recognition of the user.

17. The computer program product of claim 16, wherein the computer usable program code for storing at least one rule comprises:

computer usable program code for storing at least one rule for selecting speech recognition parameters, wherein a rule comprises an if-portion including criteria and a then-portion specifying speech recognition parameters that must be used when the criteria is met, and wherein criteria includes at least one value for at least one of time of day, recognition accuracy of the speech recognition engine, and grammar usage of the speech recognition engine.

18. The computer program product of claim 17, wherein the computer usable program code for storing at least one rule further comprises:

computer usable program code for storing at least one rule for selecting speech recognition parameters, wherein a rule comprises an if-portion including criteria and a then-portion specifying speech recognition parameters that must be used when the criteria is met, and wherein speech recognition parameters include any one of grammars, weights, accuracy settings, thresholds, and sensitivity.

19. A computer program product comprising a computer usable medium on a server for serving presence information, the computer usable medium embodying computer usable program code for providing dynamically loaded speech recognition parameters to a speech recognition engine, comprising:

computer usable program code for storing at least one rule for selecting speech recognition parameters, wherein a rule comprises an if-portion including criteria and a then-portion specifying speech recognition parameters that must be used when the criteria is met;

computer usable program code for storing periodically updated metadata about a plurality of speech recognition engines;

computer usable program code for selecting a first speech recognition engine based on most recently stored metadata;

computer usable program code for receiving notice that a speech recognition session has been initiated between a user and the first speech recognition engine;

computer usable program code for executing the at least one rule;

computer usable program code for selecting a first set of speech recognition parameters responsive to executing the at least one rule; and

computer usable program code for providing to the first speech recognition engine the first set of speech recognition parameters for performing speech recognition of the user.