Employing speech recognition and capturing customer speech to improve customer service

• US 20030115064A1
• Filed: 12/17/2001
• Published: 06/19/2003
• Est. Priority Date: 12/17/2001
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Waters, Timothy Moffett, Gusler, Carl Phillip, Hamilton, Rick Allen II
• Granted Patent: US 6,915,246 B2
• Time in Patent Office: Days
• US Class Current: 704/270
• CPC Class Codes: G10L 21/028 using properties of sound source

Abstract

The present invention comprises receiving speech input from two or more speakers, including a first speaker (such as a customer service representative for example); blocking a portion of the speech input that originates from the first speaker; and processing the remaining portion of the speech input with a computer. The blocking and processing are real-time processes, completed during a conversation. One example is a method for de-cluttering speech input for better automatic processing, by removing all but the pertinent words spoken by a customer. Another example is a system for executing methods of the present invention. A third example is a set of instructions on a computer-usable medium, or resident in a computer system, for executing methods of the present invention.

Claims

1. A method for handling information communicated by voice, said method comprising:

receiving speech input from a plurality of speakers, including a first speaker;

blocking a portion of said speech input that originates from said first speaker; and

processing the remaining portion of said speech input with a computer,

wherein said blocking and said processing are completed during a conversation involving said plurality of speakers.

2. The method of claim 1, wherein said blocking further comprises:

storing voice characteristics of said first speaker;

performing speaker recognition on said speech input;

passing to a processing function only that portion of said speech input that does not match said stored voice characteristics.

3. The method of claim 1, wherein said blocking further comprises:

providing a first speech—

input device for said first speaker;

determining whether a signal is being received from said first speech—

input device;

passing said speech input to a processing function only when no signal is being received from said first speech—

input device.

4. The method of claim 1, further comprising:

receiving a command for muting from said first speaker; and

responsive to said command, interrupting said speech input.

5. A method for handling information communicated by voice, said method comprising:

receiving speech input from a plurality of parties to a telephone conversation, including a first speaker;

blocking a portion of said speech input that originates from said first speaker; and

performing speech recognition on the remaining portion of said speech input,

wherein said blocking, and said performing speech recognition, are completed during said telephone conversation.

6. The method of claim 5, further comprising identifying key words in said remaining portion.

7. The method of claim 5, wherein said blocking further comprises:

storing voice characteristics of said first speaker;

performing speaker recognition on said speech input;

passing to a speech recognition function only that portion of said speech input that does not match said stored voice characteristics.

8. The method of claim 5, wherein said blocking further comprises:

providing a first speech—

input device for said first speaker;

determining whether a signal is being received from said first speech—

input device;

passing said speech input to a speech recognition function only when no signal is being received from said first speech—

input device.

9. The method of claim 5, further comprising:

receiving a command for muting from said first speaker; and

responsive to said command, interrupting said speech input.

10. A system for handling information communicated by voice, said system comprising:

means for receiving speech input from a plurality of parties to a telephone conversation, including a first speaker;

means for blocking a portion of said speech input that originates from said first speaker; and

means for performing speech recognition on the remaining portion of said speech input,

wherein said means for blocking, and said means for performing speech recognition, complete their operations during said telephone conversation.

11. The system of claim 10, further comprising means for identifying key words in said remaining portion.

12. The system of claim 10, wherein said means for blocking further comprises:

means for storing voice characteristics of said first speaker;

means for performing speaker recognition on said speech input;

means for passing to a speech recognition function only that portion of said speech input that does not match said stored voice characteristics.

13. The system of claim 10, wherein said means for blocking further comprises:

a first speech—

input device for said first speaker;

means for determining whether a signal is being received from said first speech—

input device;

means for passing said speech input to a speech recognition function only when no signal is being received from said first speech—

input device.

14. The system of claim 10, further comprising:

means for receiving a command for muting from said first speaker; and

means responsive to said command, for interrupting said speech input.

15. A computer-usable medium having computer-executable instructions for handling information communicated by voice, said computer-executable instructions comprising:

means for receiving speech input from a plurality of parties to a telephone conversation, including a first speaker;

means for blocking a portion of said speech input that originates from said first speaker; and

means for performing speech recognition on the remaining portion of said speech input,

wherein said means for blocking, and said means for performing speech recognition, complete their operations during said telephone conversation.

16. The computer-usable medium of claim 15, further comprising means for identifying key words in said remaining portion.

17. The computer-usable medium of claim 15, wherein said means for blocking further comprises:

means for storing voice characteristics of said first speaker;

means for performing speaker recognition on said speech input;

means for passing to a speech recognition function only that portion of said speech input that does not match said stored voice characteristics.

18. The computer-usable medium of claim 15, wherein said means for blocking further comprises:

means for determining whether a signal is being received from a first speech—

input device for said first speaker;

means for passing said speech input to a speech recognition function only when no signal is being received from said first speech—

input device.

19. The computer-usable medium of claim 15, further comprising:

means for receiving a command for muting from said first speaker; and

means responsive to said command, for interrupting said speech input.