USER INTENTION BASED ON N-BEST LIST OF RECOGNITION HYPOTHESES FOR UTTERANCES IN A DIALOG

• US 20120179467A1
• Filed: 03/20/2012
• Published: 07/12/2012
• Est. Priority Date: 12/01/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Williams, Jason
• Granted Patent: US 9,037,462 B2
• Time in Patent Office: Days
• US Class Current: 704/249
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

Disclosed herein are systems, computer-implemented methods, and tangible computer-readable media for using alternate recognition hypotheses to improve whole-dialog understanding accuracy. The method includes receiving an utterance as part of a user dialog, generating an N-best list of recognition hypotheses for the user dialog turn, selecting an underlying user intention based on a belief distribution across the generated N-best list and at least one contextually similar N-best list, and responding to the user based on the selected underlying user intention. Selecting an intention can further be based on confidence scores associated with recognition hypotheses in the generated N-best lists, and also on the probability of a user'"'"'s action given their underlying intention. A belief or cumulative confidence score can be assigned to each inferred user intention.

Claims

1. A method comprising:

receiving, as part of a spoken dialog, a user utterance;

generating, via a processor, a plurality of recognition hypothesis; and

selecting an underlying user intention based on an analysis of confidence scores, the analysis of confidence scores calculated by summing over all possible hidden user actions associated with the plurality of recognition hypothesis.

2. The method of claim 1, further comprising:

assigning an individual confidence score to each recognition hypothesis in the plurality of recognition hypothesis.

3. The method of claim 1, wherein confidence scores are operative over a whole dialog.

4. The method of claim 1, wherein the underlying user intention is further based on a probability of a user action.

5. The method of claim 1, wherein the user utterance is received during a dialog turn.

6. The method of claim 1, wherein the all possible hidden user actions form a hidden Markov model.

7. The method of claim 1, further comprising responding to the user utterance based on the underlying user intention.

8. A system comprising:

a processor; and

a non-transitory computer-readable storage medium storing instructions which, when executed on the processor, perform a method comprising;

receiving, as part of a spoken dialog, a user utterance;

generating a plurality of recognition hypothesis; and

selecting an underlying user intention based on an analysis of confidence scores, the analysis of confidence scores calculated by summing over all possible hidden user actions associated with the plurality of recognition hypothesis.

9. The system of claim 8, the instructions causing the method to further comprise:

assigning an individual confidence score to each recognition hypothesis in the plurality of recognition hypothesis.

10. The system of claim 9, wherein confidence scores are operative over a whole dialog.

11. The system of claim 9, wherein the underlying user intention is further based on a probability of a user action.

12. The system of claim 9, wherein the user utterance is received during a dialog turn.

13. The system of claim 9, wherein the all possible hidden user actions form a hidden Markov model.

14. The system of claim 9, the instructions causing the method to further comprise responding to the user utterance based on the underlying user intention.

15. A non-transitory computer-readable storage medium storing instructions which, when executed on a computing device, cause the computing device to perform steps comprising:

receiving, as part of a spoken dialog, a user utterance;

generating a plurality of recognition hypothesis; and

selecting an underlying user intention based on an analysis of confidence scores, the analysis of confidence scores calculated by summing over all possible hidden user actions associated with the plurality of recognition hypothesis.

16. The non-transitory computer-readable storage medium of claim 15, the steps further comprising:

assigning an individual confidence score to each recognition hypothesis in the plurality of recognition hypothesis.

17. The non-transitory computer-readable storage medium of claim 15, wherein confidence scores are operative over a whole dialog.

18. The non-transitory computer-readable storage medium of claim 15, wherein the underlying user intention is further based on a probability of a user action.

19. The non-transitory computer-readable storage medium of claim 15, wherein the user utterance is received during a dialog turn.

20. The non-transitory computer-readable storage medium of claim 15, wherein the all possible hidden user actions form a hidden Markov model.