Tuning Reusable Software Components in a Speech Application

• US 20080077402A1
• Filed: 09/22/2006
• Published: 03/27/2008
• Est. Priority Date: 09/22/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Silva, Aimee, Mandalia, Baiju D., Dhanakshirur, Girish
• Granted Patent: US 8,386,248 B2
• Time in Patent Office: Days
• US Class Current: 704/231
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A method of tuning reusable dialog components within a speech application can include detecting speech recognition events generated from a plurality of recognitions performed for a field of a reusable dialog component. The speech recognition events can be generated over a plurality of interactive voice response sessions. The method also can include automatically computing a suggested value for a tuning parameter corresponding to the field of the reusable dialog component according, at least in part, to the speech recognition events.

Claims

1. A method of tuning reusable dialog components within a speech application comprising:

detecting speech recognition events generated from a plurality of recognitions performed for a field of a reusable dialog component, wherein the speech recognition events are generated over a plurality of interactive voice response sessions; and

automatically computing a suggested value for a tuning parameter corresponding to the field of the reusable dialog component according, at least in part, to the speech recognition events.

2. The method of claim 1, wherein automatically computing a suggested value further comprises applying a statistical processing technique to values specified by the speech recognition events.

3. The method of claim 2, wherein applying a statistical processing technique further comprises determining an average of the values of the speech recognition events.

4. The method of claim 1, further comprising selecting a particular speech recognition event type to be detected, wherein only speech recognition events of the particular type are used to determine the suggested value of the tuning parameter.

5. The method of claim 1, further comprising:

storing the suggested value of the tuning parameter within a model comprising suggested values of tuning parameters for the reusable dialog component; and

upon a further execution of the reusable dialog component, initializing the tuning parameter of the reusable dialog component using the suggested value of the tuning parameter from the model.

6. The method of claim 1, further comprising:

storing the suggested value of the tuning parameter within a model comprising suggested values of tuning parameters for the reusable dialog component; and

providing an interface that facilitates real-time access to the model, wherein the interface facilitates observance of the tuning parameters as the tuning parameters are dynamically updated as operation of the interactive voice response system continues.

7. The method of claim 1, further comprising computing a plurality of suggested values for the tuning parameter as operation of the interactive voice response system continues and storing the plurality of suggested values of the tuning parameter.

8. The method of claim 1, further comprising counting each instantiation of the reusable dialog component over the plurality of interactive voice response sessions.

9. A system for tuning reusable dialog components within a speech application comprising:

at least one reusable dialog component, wherein the reusable dialog component comprises at least one tunable parameter;

a listener configured to detect speech recognition events generated during execution of the reusable dialog component, wherein the speech recognition events have a specific type and are associated with a particular field of the reusable dialog component; and

a model comprising estimated tuning parameter information for the reusable dialog component,

wherein the listener calculates a suggested value for a tuning parameter of the particular field of the reusable dialog component according, at least in part, to the detected speech recognition events and stores the suggested value within the model.

10. The system of claim 9, wherein the listener applies a statistical processing technique to values specified by the detected speech recognition events to calculate the suggested value for the tuning parameter.

11. The system of claim 9, wherein the listener calculates a suggested value for a tuning parameter of the particular field of the reusable dialog component using only the speech recognition events that are of a specified type.

12. The system of claim 9, wherein the reusable dialog component, upon execution, initializes the tuning parameter using the suggested value stored in the model.

13. A machine readable storage, having stored thereon a computer program having a plurality of code sections for tuning reusable dialog components within a speech application, the machine readable storage comprising:

code for detecting speech recognition events generated from a plurality of recognitions performed for a field of a reusable dialog component, wherein the speech recognition events are generated over a plurality of interactive voice response sessions; and

code for automatically computing a suggested value for a tuning parameter corresponding to the field of the reusable dialog component according, at least in part, to the speech recognition events.

14. The machine readable storage of claim 13, wherein the code for automatically computing a suggested value further comprises code for applying a statistical processing technique to values specified by the speech recognition events.

15. The machine readable storage of claim 14, wherein the code for applying a statistical processing technique further comprises code for determining an average of the values of the speech recognition events.

16. The machine readable storage of claim 13, further comprising code for selecting a particular speech recognition event type to be detected, wherein only speech recognition events of the particular type are used to determine the suggested value of the tuning parameter.

17. The machine readable storage of claim 13, further comprising:

code for storing the suggested value of the tuning parameter within a model comprising suggested values of tuning parameters for the reusable dialog component; and

code for, upon a further execution of the reusable dialog component, initializing the tuning parameter of the reusable dialog component using the suggested value of the tuning parameter from the model.

18. The machine readable storage of claim 13, further comprising:

code for storing the suggested value of the tuning parameter within a model comprising suggested values of tuning parameters for the reusable dialog component; and

code for providing an interface that facilitates real-time access to the model, wherein the interface facilitates observance of the tuning parameters as the tuning parameters are dynamically updated as operation of the interactive voice response system continues.

19. The machine readable storage of claim 13, further comprising code for computing a plurality of suggested values for the tuning parameter as operation of the interactive voice response system continues and storing the plurality of suggested values for the tuning parameter.

20. The machine readable storage of claim 13, further comprising code for counting each instantiation of the reusable dialog component over the plurality of interactive voice response sessions.