In-band signaling in interactive communications

• US 8,532,269 B2
• Filed: 01/16/2009
• Issued: 09/10/2013
• Est. Priority Date: 01/16/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Chambers, Robert L., Coryell, Larry, Kaushansky, Karen J., Odell, Julian James, Chou, Jim C.
• Primary Examiner(s): Sing, Simon
• Assistant Examiner(s): BEZUAYEHU, SOLOMON G
• Application Number:
  US12/354,799
• Publication Number:
  US 20100183126A1
• Time in Patent Office: 1,698 Days
• Field of Search: 379 8801- 8822
• US Class Current: 379/88.04
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 21/02 Speech enhancement, e.g. noise reduction or echo cancellation reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04Q 1/45 using multi-frequency signalling H04Q1/46 takes precedence

Abstract

Architecture that employs a combination of in-band signaling (e.g., DTMF) with speech recognition to deliver usability improvements. The in-band signaling allows the user to indicate to the system when a barge-in operation is occurring and/or when to start listening to subsequent speech input and optionally, when to stop listening for further speech input. The in-band signaling can be utilized during a telephone call and using wireline and wireless telephones. Moreover, the architecture can be incorporated at the platform level requiring little, if any, application changes to support the new mode of operation.

Claims

1. An interactive voice response system for conducting voice response communications, the interactive voice response system comprising:

at least one processor; and

a computer readable medium having executable instructions stored thereupon which, when executed by the at least one processor, cause the at least one processor to

initiate a marker mode at the interactive voice response system;

begin playing of a message prompt;

receive, at the interactive voice response system, a first marker signal, a second marker signal, and voice signals;

interrupt the playing of the message prompt in response to receiving the first marker signal;

identify, based upon the first marker signal, a beginning of a voice command represented by the voice signals;

identify, based upon the second marker signal, at least one of a beginning of a voice command;

ignore at least a portion of audio signals received at the interactive voice response system before the first marker signal and after the second marker signal; and

take an action, in response to the voice command.

2. The system of claim 1, wherein initiating the marker mode comprises initiating the marker mode in response to receiving the first marker signal.

3. The system of claim 1, wherein the computer readable medium has further executable instructions stored thereupon which, when executed by the processor, cause the interactive voice response system to send an instruction to input a further marker signal for further communications.

4. The method of claim 1, further comprising receiving a further marker signal and designating, based upon the marker signal and the further marker signal, the beginning of the voice command and the end of the voice command.

5. The system of claim 1, wherein receiving the marker signal comprises receiving a dual-tone multi-frequency signal.

6. The system of claim 1, wherein the computer readable medium has further executable instructions stored thereupon which, when executed by the processor, cause the interactive voice response system to initiate a non-marker mode of operation at the interactive voice response system in response to determining that the audio does not include background noise.

7. The system of claim 1, wherein receiving the first marker signal comprises receiving a signal generated by a mobile device in response to a command received at a vehicle.

18. The method of claim 1, wherein ignoring, based on receiving the marker signal, audio signals received at the interactive voice response system comprises ignoring audio signals that are not associated with a voice command.

19. The method of claim 18, wherein ignoring signals that are not associated with a voice command comprises ignoring background noise.

8. A computer-implemented method for conducting voice response communications, the method comprising:

initiating a marker mode at an interactive voice response system;

beginning playing of a message prompt;

receiving, at the interactive voice response system, a first marker signal, voice signals, and a second marker signal;

interrupting the playing of the message prompt in response to receiving the first marker signal;

identifying, based upon the first marker signal, a beginning of a voice command represented by the voice signals;

identifying, based upon the second marker signal, an end of the voice command;

ignoring at least a portion of audio signals received at the interactive voice response system before the first marker signal and after the second marker signal; and

taking an action, in response to the voice command.

9. The method of claim 8, further comprising sending an instruction to input a further marker signal for further communications.

10. The method of claim 8, wherein receiving the first marker signal comprises receiving a first dual-tone multi-frequency signal and wherein receiving the second marker signal comprises receiving a second dual-tone multi-frequency signal.

11. The method of claim 8, wherein receiving the first marker signal comprises receiving a first voice command and wherein receiving the second marker signal comprises receiving a second voice command.

12. The method of claim 8, further comprising initiating a non-marker mode of operation at the interactive voice response system in response to determining that the audio does not include background noise.

13. The method of claim 8, wherein receiving the first marker signal comprises receiving a signal generated by a mobile telephone in response to a command received at a vehicle.

14. The method of claim 8, wherein initiating the marker mode comprises initiating the marker mode in response to receiving the marker signal.

15. A tangible computer-readable medium comprising computer-executable instructions stored thereon that, when executed by a computer, cause the computer to:

initiate a marker mode at an interactive voice response system;

receive, at the interactive voice response system, a first marker signal, a voice signal, and a second marker signal;

identify, based upon the first marker signal, a beginning of a voice command represented by the voice signal;

identify, based upon the second marker signal, an end of the voice command;

ignore at least a portion of audio signals received at the interactive voice response system before the first marker signal and after the second marker signal;

playing a message prompt, in response to the voice command; and

interrupting the playing of the message prompt in response to receiving a third marker signal.

16. The tangible computer-readable medium of claim 15, further comprising sending an instruction to input a further marker signal for further communications.

17. The tangible computer-readable medium of claim 15, wherein receiving the first marker signal comprises receiving a first dual-tone multi-frequency signal and wherein receiving the second marker signal comprises receiving a second dual-tone multi-frequency signal.