System and method for using a library to interactively design natural language spoken dialog systems

• US 20060149553A1
• Filed: 01/05/2005
• Published: 07/06/2006
• Est. Priority Date: 01/05/2005
• Status: Abandoned Application

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Tru, Gokhan, Gibbon, David Crawford, Shahraray, Behzad, Liu, Zhu, Renger, Bernard S., Begeja, Lee, Fabbrizio, Giuseppe Di
• Application Number:
  US11/029,317
• Publication Number:
  US 20060149553A1
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

Aspects of the invention pertain to a system for using a library to interactively design natural language spoken dialog systems. The system may include a processing device and an extractor. The processing device may be configured to receive user input selections indicating ones of a group of spoken dialog data stored in a library. The extractor may be configured to extract the ones of the group of spoken dialog data and a model building module may be configured to build one of a Spoken Language Understanding (SLU) model or an Automatic Speech Recognition (ASR) model based on the extracted ones of the plurality of spoken dialog data.

Claims

1. A method for using a library of reusable spoken language dialog components, the method comprising:

receiving user input indicating selections of spoken language dialog data from the library;

extracting the selections of spoken language dialog data from the library; and

building one of a Spoken Language Understanding (SLU) model or an Automatic Speech Recognition (ASR) model based on the selected spoken language dialog data.

2. The method of claim 1, further comprising:

bootstrapping a new spoken dialog system using the built SLU model or the built ASR model.

3. The method of claim 1, wherein:

the selections of spoken language dialog data include utterance data.

4. The method of claim 1, wherein:

the library includes the plurality of spoken language dialog data organized into a plurality of sectors.

5. The method of claim 4, wherein:

each of the sectors includes spoken dialog data pertaining to an industrial sector.

6. The method of claim 4, wherein:

each of the sectors includes at least one collection corresponding to utterance data collected during a particular timeframe.

7. The method of claim 6, wherein:

each of the at least one collection includes the corresponding utterance data stored according to at least one category.

8. The method of claim 7, wherein:

each of the at last one category includes corresponding utterance data stored according to at least one call-type.

9. A system for reusing spoken dialog components, the system comprising:

a processing device configured to receive user input selections indicating ones of a plurality of spoken dialog data stored in a library;

an extractor configured to extract the ones of the plurality of spoken dialog data; and

a model building module configured to build one of a Spoken Language Understanding (SLU) model or an Automatic Speech Recognition (ASR) model based on the extracted ones of the plurality of spoken dialog data.

10. The system of claim 9, wherein the extractor comprises the model building module.

11. The system of claim 9, wherein the extractor is included in the processing device.

12. The system of claim 9, wherein the processing device is further configured to bootstrap a new spoken dialog application using at least one of the SLU model or the ASR model.

13. The system of claim 9, further comprising the library of reusable spoken dialog components.

14. The system of claim 9, wherein the ones of the plurality of spoken dialog data include utterance data.

15. The system of claim 13, wherein the library includes the plurality of spoken dialog data organized into a plurality of sectors.

16. The system of claim 15, wherein each of the sectors includes spoken dialog data pertaining to a different industrial sector.

17. The system of claim 15, wherein each of the sectors includes at least one collection including spoken dialog data collected during a particular timeframe.

18. The system of claim 17, wherein each of the at least one collection includes the corresponding spoken dialog data stored according to at least one category.

19. The system of claim 18, wherein each of the at least one category includes corresponding utterance data stored according to at least one call-type.

20. A machine-readable medium having recorded therein instructions for a processor, the instructions comprising:

a set of instructions for receiving user input indicating selections of spoken language dialog data from a library;

a set of instructions for extracting the selections of spoken language dialog data from the library; and

a set of instructions for building at least one of an Automatic Speech Recognition (ASR) model or a Spoken Language Understanding (SLU) model based on the selected spoken language dialog data.

21. The machine-readable medium of claim 20, further comprising:

a set of instructions for bootstrapping a new spoken dialog system using at least one of the ASR model or the SLU model.

22. The machine-readable medium of claim 20, wherein:

the selections of spoken language dialog data include utterance data.

23. The machine-readable medium of claim 20, wherein:

the library includes the plurality of spoken language dialog data organized into a plurality of sectors.

24. The machine-readable medium of claim 23, wherein:

each of the sectors includes spoken dialog data pertaining to an industrial sector.

25. The machine-readable medium of claim 23, wherein:

each of the sectors includes at least one collection corresponding to utterance data collected during a particular timeframe.

26. The machine-readable medium of claim 25, wherein:

each of the at least one collection includes the corresponding utterance data stored according to at least one category.

27. The machine-readable medium of claim 26, wherein:

each of the at last one category includes corresponding utterance data stored according to at least one call-type.

28. A system for reusing spoken dialog components, the system comprising:

means for receiving user input indicating selections of spoken language dialog data from a library of reusable components;

means for extracting the selections of spoken language dialog data from the library; and

means for building at least one of a Spoken Language Understanding (SLU) model or an Automatic Speech Recognition (ASR) model based on the selected spoken language dialog data.