System and method for improving interaction with a user through a dynamically alterable spoken dialog system

• US 8,024,179 B2
• Filed: 10/30/2007
• Issued: 09/20/2011
• Est. Priority Date: 10/30/2007
• Status: Active Grant

• Current Assignee: AT&T Corporation (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Zhang, Lan, Blanchard, Harry E., Pulz, Gregory, Lewis, Steven H.
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US11/929,306
• Publication Number:
  US 20090112590A1
• Time in Patent Office: 1,421 Days
• Field of Search: 704/10, 704/246, 704/275, 369/25.01
• US Class Current: 704/10
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams

Abstract

Disclosed are systems and methods for dynamically interacting with a user through a spoken dialogue system. A method includes the steps of (1) receiving a user utterance, (2) analyzing the user utterance for a threshold determination of dialect, (3) generating a response that reflects an incremental implementation of the dialect, (4) further varying the perceived implementation of the dialect in subsequent responses by a process of: (a) receiving a subsequent user utterance, (b) determining a modified level of confidence in the dialect based at least in part from the subsequent utterance, (c) generating a subsequent response that implements an incremental variation according to the modified level of confidence.

Claims

1. A method for dynamically interacting with a user through a spoken dialogue system, the method comprising:

receiving a user utterance;

analyzing the user utterance for a threshold determination of a dialect;

generating a response that reflects an incremental implementation of the dialect;

further varying a perceived implementation of the dialect in subsequent responses by a process of;

(a) receiving a subsequent user utterance;

(b) determining a modified level of confidence in the dialect based at least in part from the subsequent utterance; and

(c) generating a subsequent response that implements an incremental variation according to the modified level of confidence.

2. The method of claim 1 wherein the response is incrementally varied by modifying a parameter selected from the group consisting of verbiage, vocabulary, pronunciation, phrasing, pauses, and prosody.

3. The method of claim 1 further comprising:

receiving at least one successive user utterance;

applying process steps (a)-(c) iteratively to the at least one successive user utterance.

4. The method of claim 3 further comprising generating at least one successive response, wherein the at least one successive response tracks the dialect of the at least one successive user utterance.

5. The method of claim 1 wherein the perceived implementation of the dialect becomes stronger.

6. The method of claim 1 wherein the perceived implementation of the dialect becomes weaker.

7. The method of claim 1 further comprising:

receiving at least a third user utterance;

determining a higher level of confidence in the dialect based at least in part from the at least third user utterance; and

generating at least a third response that implements an incremental variation according to the higher level of confidence.

8. A spoken dialogue system comprising a plurality of program modules embodied in at least one of non-transitory, computer readable and executable media, including:

a processor;

a first module configured to control the processor to receive a user utterance;

a second module configured to control the processor to analyze the user utterance for a threshold determination of a dialect;

a third module configured to control the processor to generate a response that reflects an incremental implementation of the dialect;

a fourth module configured to control the processor to further vary a perceived implementation of the dialect wherein the module to further vary the perceived implementation of the dialect is configured to receive a subsequent user utterance, determine a modified level of confidence in the dialect based at least in part from the subsequent utterance, and generate a subsequent response that implements an incremental variation according to the modified level of confidence.

9. The system of claim 8 wherein the third module is further configured to vary the response incrementally by modifying a parameter selected from the group consisting of verbiage, vocabulary, pronunciation, phrasing, pauses, and prosody.

10. The system of claim 8 further comprising:

a fifth module configured to control the processor to receive at least one successive user utterance; and

a sixth module configured to control the processor to iteratively vary the perceived implementation of the dialect wherein the module to iteratively vary the perceived implementation of the dialect is configured to receive the at least one successive user utterance, determine a successive level of confidence in the dialect based at least in part from the at least one successive user utterance, and generate a successive response that implements an incremental variation according to the successive level of confidence.

11. The system of claim 10 further comprising a seventh module configured to control the processor to generate at least one successive response, wherein the at least one successive response tracks the dialect of the at least one successive user utterance.

12. The system of claim 8 wherein the perceived implementation of the dialect becomes stronger.

13. The system of claim 8 wherein the fourth module configured to control the processor to further vary the perceived implementation of the dialect modifies the dialect to becomes weaker.

14. A non-transitory computer readable medium storing computer-executable instructions for a computing device to function as a spoken dialogue system, the instructions comprising:

receiving a user utterance;

analyzing the user utterance for a threshold determination of a dialect;

generating a response that reflects an incremental implementation of the dialect;

further varying a perceived implementation of the dialect in subsequent responses by a process of;

(a) receiving a subsequent user utterance;

(b) determining a modified level of confidence in the dialect based at least in part from the subsequent utterance; and

(c) generating a subsequent response that implements an incremental variation according to the modified level of confidence.

15. The non-transitory computer readable medium of claim 14 wherein the instructions provide that the response be incrementally varied by modifying a parameter selected from the group consisting of verbiage, vocabulary, pronunciation, phrasing, pauses, and prosody.

16. The non-transitory computer readable medium of claim 14 further comprising:

receiving at least one successive user utterance;

applying process steps (a)-(c) iteratively to the at least one successive user utterance.

17. The non-transitory computer readable medium of claim 16 further comprising generating at least one successive response, wherein the at least one successive response tracks the dialect of the at least one successive user utterance.

18. The non-transitory computer readable medium of claim 14 wherein the instructions change the perceived implementation of the dialect to become stronger.

19. The non-transitory computer readable medium of claim 14 wherein the instructions change the perceived implementation of the dialect to become weaker.

20. The non-transitory computer readable medium of claim 14 further comprising:

receiving at least a third user utterance;

determining a higher level of confidence in the dialect based at least in part from the at least third user utterance; and

generating at least a third response that implements an incremental variation according to the higher level of confidence.