Real time automatic caller speech profiling

• US 8,358,747 B2
• Filed: 11/10/2009
• Issued: 01/22/2013
• Est. Priority Date: 11/10/2009
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Daye, Sheri G., Jaiswal, Peeyush, Wang, Fang
• Primary Examiner(s): ISLAM, MOHAMMAD K
• Application Number:
  US12/615,384
• Publication Number:
  US 20110110502A1
• Time in Patent Office: 1,169 Days
• Field of Search: 379 8801- 8823, 379/265.02, 704/9, 704/246, 704/257, 704/273, 704/250, 709/204
• US Class Current: 379/88.01
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2203/2061 Language aspects
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A computer-implemented method, system, and computer program product for recognizing a voice input to an interactive voice recognition system is presented. An initial caller voice input is received from a caller. In response to determining that the initial caller voice input is a computer-unintelligible voice input that does not match any entry from a lexicon of known voice inputs, the caller is prompted to transmit a secondary input to clarify the computer-unintelligible voice input. The secondary input is utilized to match the computer-unintelligible voice input with a specific known voice input from the lexicon of known voice inputs. The lexicon of known voice inputs is then updated with the computer-unintelligible voice input.

Claims

1. A computer-implemented method of recognizing a voice input received by an interactive voice recognition system, the computer-implemented method comprising:

receiving an initial caller voice input from a caller, wherein the initial caller voice input is the caller saying an unintelligible phrase caused by a speech limitation of the caller;

a processor determining that the initial caller voice input is a computer-unintelligible voice input that does not match any entry from a lexicon of known voice inputs;

prompting the caller to transmit a secondary input to clarify the computer-unintelligible voice input, wherein the secondary input is a dual-tone multi-frequency (DTMF) phone keypad input from the caller that identifies a user-requested activity that the caller was requesting when saying the unintelligible phrase;

utilizing the secondary input to match the computer-unintelligible voice input with a specific known voice input from the lexicon of known voice inputs; and

updating the lexicon of known voice inputs with the computer-unintelligible voice input, wherein the computer-unintelligible voice input is matched to the specific known voice input from the lexicon of known voice inputs;

matching the unintelligible phrase to the user-requested activity in a database that is specific for the caller;

receiving the unintelligible phrase in a subsequent phone call from the user; and

matching the unintelligible phrase to the user-requested activity for the caller.

2. The computer-implemented method of claim 1, wherein the secondary input further comprises another caller voice input from the caller.

3. The computer-implemented method of claim 2, further comprising:

in response to said another caller voice input from the caller matching the specific known voice input, discarding said another caller voice input from the lexicon of known voice inputs.

4. The computer-implemented method of claim 1, wherein the secondary input is a caller'"'"'s response to a menu of input options, wherein one of the input options identifies an input whose definition matches that of the specific known voice input from the lexicon of known voice inputs.

5. The computer-implemented method of claim 1, wherein the lexicon of known voice inputs is exclusive to the caller.

6. The computer-implemented method of claim 1, wherein the lexicon of known voice inputs is non-exclusive to the caller.

7. The computer-implemented method of claim 1, further comprising:

matching the computer-unintelligible voice input to an interactive voice recognition activity; and

utilizing a match between the computer-unintelligible voice input and the interactive voice recognition activity to match the computer-unintelligible voice input to the specific known voice input from the lexicon of known voice inputs.

8. The computer-implemented method of claim 1, wherein updating the lexicon of known voice inputs with the computer-unintelligible voice input creates an updated lexicon of known voice inputs, the computer-implemented method further comprising:

receiving a new call from the caller, wherein the caller transmits a new caller voice input;

matching the new caller voice input with a known voice input from the updated lexicon of known voice inputs.

20. The computer-implemented method of claim 1, wherein the initial caller voice input is the caller saying a first phrase, wherein the secondary input further comprises the caller saying a second phrase that is different from the first phrase, wherein the first phrase and the second phrase describe a same user-requested activity, and wherein the computer-implemented method further comprises:

matching the first phrase and the second phrase to the same user-requested activity, wherein the matching is specific for the caller.

9. A computer program product for recognizing a voice input received by an interactive voice recognition system, the computer program product comprising:

a computer readable non-transitory storage media;

first program instructions to receive an initial caller voice input from a caller, wherein the initial caller voice input is the caller saying an unintelligible phrase caused by a speech limitation of the caller;

second program instructions to determine that the initial caller voice input is a computer-unintelligible voice input that does not match any entry from a lexicon of known voice inputs;

third program instructions to prompt the caller to transmit a secondary input to clarify the computer-unintelligible voice input, wherein the secondary input is a dual-tone multi-frequency (DTMF) phone keypad input from the caller that identifies a user-requested activity that the caller was requesting when saying the unintelligible phrase;

fourth program instructions to utilize the secondary input to match the computer-unintelligible voice input with a specific known voice input from the lexicon of known voice inputs; and

fifth program instructions to update the lexicon of known voice inputs with the computer-unintelligible voice input, wherein the computer-unintelligible voice input is matched to the specific known voice input from the lexicon of known voice inputs;

sixth program instructions to match the unintelligible phrase to the user-requested activity in a database that is specific for the caller;

seventh program instructions to receive the unintelligible phrase in a subsequent phone call from the user; and

eighth program instructions to match the unintelligible phrase to the user-requested activity for the caller; and

wherein

the first, second, third, fourth, fifth, sixth, seventh, and eighth program instructions are stored on the computer readable storage media.

10. The computer program product of claim 9, wherein the secondary input further comprises another caller voice input from the caller.

11. The computer program product of claim 10, further comprising:

ninth program instructions to, in response to said another caller voice input from the caller matching the specific known voice input, discard said another caller voice input from the lexicon of known voice inputs; and

wherein

the ninth program instructions are stored on the computer readable storage media.

12. The computer program product of claim 9, wherein the secondary input is a caller'"'"'s response to a menu of input options, wherein one of the input options identifies an input whose definition matches that of the specific known voice input from the lexicon of known voice inputs.

13. The computer program product of claim 9, wherein the lexicon of known voice inputs is exclusive to the caller.

14. The computer program product of claim 9, wherein the lexicon of known voice inputs is non-exclusive to the caller.

15. The computer program product of claim 9, further comprising:

ninth program instructions to match the computer-unintelligible voice input to an interactive voice recognition activity; and

tenth program instructions to utilize a match between the computer-unintelligible voice input and the interactive voice recognition activity to match the computer-unintelligible voice input to the specific known voice input from the lexicon of known voice inputs; and

wherein

the ninth and tenth program instructions are stored on the computer readable storage media.

16. The computer program product of claim 9, wherein updating the lexicon of known voice inputs with the computer-unintelligible voice input creates an updated lexicon of known voice inputs, the computer-implemented method further comprising:

ninth program instructions to receive a new call from the caller, wherein the caller transmits a new caller voice input;

tenth program instructions to match the new caller voice input with a known voice input from the updated lexicon of known voice inputs; and

wherein

the ninth and tenth program instructions are stored on the computer readable storage media.

17. The computer program product of claim 9, wherein the first, second, third, fourth, fifth, sixth, seventh, and eighth program instructions are downloaded to the computer readable storage media from a remote software deploying server in an on-demand basis.

18. A computer system comprising:

a processor, a computer readable memory, and a computer readable non-transitory storage media;

first program instructions to receive an initial caller voice input from a caller, wherein the initial caller voice input is the caller saying an unintelligible phrase caused by a speech limitation of the caller;

second program instructions to determine that the initial caller voice input is a computer-unintelligible voice input that does not match any entry from a lexicon of known voice inputs;

third program instructions to prompt the caller to transmit a secondary input to clarify the computer-unintelligible voice input, wherein the secondary input is a dual-tone multi-frequency (DTMF) phone keypad input from the caller that identifies a user-requested activity that the caller was requesting when saying the unintelligible phrase;

fourth program instructions to utilize the secondary input to match the computer-unintelligible voice input with a specific known voice input from the lexicon of known voice inputs; and

fifth program instructions to update the lexicon of known voice inputs with the computer-unintelligible voice input, wherein the computer-unintelligible voice input is matched to the specific known voice input from the lexicon of known voice inputs;

sixth program instructions to match the unintelligible phrase to the user-requested activity in a database that is specific for the caller;

seventh program instructions to receive the unintelligible phrase in a subsequent phone call from the user; and

eighth program instructions to match the unintelligible phrase to the user-requested activity for the caller; and

wherein

the first, second, third, fourth, fifth, sixth, seventh, and eighth program instructions are stored on the computer readable storage media for execution by the processor via the computer readable memory.

19. The computer system of claim 18, wherein the lexicon of known voice inputs is exclusive to the caller.