DYNAMIC UPDATE OF GRAMMAR FOR INTERACTIVE VOICE RESPONSE

• US 20100114564A1
• Filed: 11/04/2008
• Published: 05/06/2010
• Est. Priority Date: 11/04/2008
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Data Services LLC (Verizon Communications Inc.)
• Inventors: KESIREDDY, Manohar R.
• Granted Patent: US 8,374,872 B2
• Time in Patent Office: Days
• US Class Current: 704/10
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A device provides a question to a user, and receives, from the user, an unrecognized voice response to the question. The device also provides the unrecognized voice response to an utterance agent for determination of the unrecognized voice response without user involvement, and provides an additional question to the user prior to receiving the determination of the unrecognized voice response from the utterance agent.

Claims

1. A computing device-implemented method, comprising:

providing a question to a user;

receiving, from the user, an unrecognized voice response to the question;

providing the unrecognized voice response to an utterance agent associated with the computing device for determination of the unrecognized voice response without user involvement; and

providing an additional question to the user prior to receiving the determination of the unrecognized voice response from the utterance agent.

2. The computing device-implemented method of claim 1, further comprising:

receiving, from the user, a recognized voice response to the additional question; and

storing the recognized voice response.

3. The computing device-implemented method of claim 2, where the recognized voice response is decipherable by a grammar/voice recognition component associated with the computing device.

4. The computing device-implemented method of claim 1, where providing the unrecognized voice response to an utterance agent comprises:

reviewing, with the utterance agent, the unrecognized voice response in real time;

determining, with the utterance agent, a deciphered response based on the real time review of the unrecognized voice response; and

updating, in real time and with the deciphered response, a grammar component associated with the computing device.

5. The computing device-implemented method of claim 1, where the computing device comprises an interactive voice response (IVR) server.

6. The computing device-implemented method of claim 1, where the computing device comprises a user device.

7. The computing device-implemented method of claim 6, where the user device comprises one or more of:

a radiotelephone,

a personal communications system (PCS) terminal,

a personal digital assistant (PDA),

a laptop computer,

a personal computer,

a set-top box (STB),

a television, or

a personal gaming system.

8. The computing device-implemented method of claim 1, where the unrecognized voice response includes an utterance that is indecipherable by a grammar/voice recognition component associated with the computing device.

9. A computer-readable memory device that stores computer-executable instructions, comprising:

one or more instructions for providing a query to a user;

one or more instructions for receiving, from the user, an unrecognized voice response to the query;

one or more instructions for providing the unrecognized voice response to an utterance agent for determination of the unrecognized voice response without requesting clarification from the user; and

one or more instructions for providing an additional query to the user prior to receiving the determination of the unrecognized voice response from the utterance agent.

10. The computer-readable memory device of claim 9, where the computer-readable memory device is provided in an interactive voice response (IVR) server.

11. The computer-readable memory device of claim 9, where the computer-readable memory device is provided in a user device.

12. The computer-readable memory device of claim 11, where the user device comprises one or more of:

a radiotelephone,

a personal communications system (PCS) terminal,

a personal digital assistant (PDA),

a laptop computer,

a personal computer,

a set-top box (STB),

a television, or

a personal gaming system.

13. The computer-readable memory device of claim 9, further comprising:

one or more instructions for receiving, from the user, a recognized voice response to the additional query; and

one or more instructions for storing the recognized voice response in the computer-readable memory device.

14. The computer-readable memory device of claim 13, where the recognized voice response is decipherable by a grammar/voice recognition component.

15. The computer-readable memory device of claim 9, where the one or more instructions for providing the unrecognized voice response to an utterance agent comprises:

one or more instructions for reviewing, with the utterance agent, the unrecognized voice response in real time;

one or more instructions for determining, with the utterance agent, a deciphered response based on the real time review of the unrecognized voice response; and

one or more instructions for updating, in real time and with the deciphered response, a grammar component.

16. The computer-readable memory device of claim 9, where the unrecognized voice response includes an utterance that is indecipherable by a grammar/voice recognition component.

17. A device, comprising:

a memory to store a plurality of instructions; and

a processor to execute instructions in the memory to;

provide a question to a user,

receive, from the user, an unrecognized voice response to the question,

provide the unrecognized voice response to an utterance agent associated with the device for determination of the unrecognized voice response, where the determination of the unrecognized voice response is transparent to the user, and

provide an additional question to the user prior to receiving the determination of the unrecognized voice response from the utterance agent.

18. The device of claim 17, where the processor further executes instructions in the memory to:

receive, from the user, a recognized voice response to the additional question, and

store the recognized voice response in the memory.

19. The device of claim 18, where the recognized voice response is decipherable by a grammar/voice recognition component associated with the device.

20. The device of claim 17, where the processor further executes instructions in the memory to:

review, with the utterance agent, the unrecognized voice response in real time,

determine, with the utterance agent, a deciphered response based on the real time review of the unrecognized voice response, and

update, in real time and with the deciphered response, a grammar component associated with the device.

21. The device of claim 17, where the device comprises an interactive voice response (IVR) server.

22. The device of claim 17, where the device comprises a user device.

23. The device of claim 22, where the user device comprises one or more of:

a radiotelephone,

a personal communications system (PCS) terminal,

a personal digital assistant (PDA),

a laptop computer,

a personal computer,

a set-top box (STB),

a television, or

a personal gaming system.

24. The device of claim 17, where the unrecognized voice response includes an utterance that is indecipherable by a grammar/voice recognition component associated with the device.

25. A system, comprising:

a grammar/voice recognition component configured to;

receive, from a user and via a user device associated with the user, an unrecognized voice response to a question,

attempt to decipher the unrecognized voice response, and

provide the unrecognized voice response to an utterance agent component when the attempt to decipher the unrecognized voice response fails; and

the utterance agent component being configured to;

review the unrecognized voice response in real time,

determine a deciphered response based on the real time review of the unrecognized voice response and without requesting clarification from the user, and

update, in real time, the grammar/voice recognition component with the deciphered response.