IN-BAND SIGNALING IN INTERACTIVE COMMUNICATIONS

• US 20100183126A1
• Filed: 01/16/2009
• Published: 07/22/2010
• Est. Priority Date: 01/16/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Chou, Jim C., Coryell, Larry, Kaushansky, Karen J., Chambers, Robert L., Odell, Julian James
• Granted Patent: US 8,532,269 B2
• Time in Patent Office: Days
• US Class Current: 379/88.40
• 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. A computer-implemented voice response communications system, comprising:

an interactive voice response component for sending message prompts and receiving voice signals via an in-band channel; and

an in-band signaling component for inputting a marker signal relative to a voice signal to delineate the voice signal in presence of background noise received into the in-band channel.

2. The system of claim 1, wherein the interactive voice response component automatically enables processing of the marker signal via the in-band channel in response to an amount of the background noise that impacts speech recognition accuracy.

3. The system of claim 1, wherein the marker signal is input prior to initiating the voice signal to designate a starting point of the voice signal.

4. The system of claim 1, wherein the marker signal is input after termination of the voice signal to designate an ending point of the voice signal.

5. The system of claim 1, wherein the marker signal is input prior to initiating the voice signal to designate a starting point of the voice signal, and after termination of the voice signal to designate an ending point of the voice signal.

6. The system of claim 1, wherein the marker signal is input using a dual-tone multi-frequency (DTMF) signal generated in association with a key of a keypad of a communications device that is handheld or vehicle-based.

7. The system of claim 1, wherein the interactive voice response component automatically sends an instruction for how to input the marker signal.

8. The system of claim 7, wherein the interactive voice response component automatically sends the instruction in response to reduced accuracy of an associated speech recognition engine due to the background noise.

9. The system of claim 7, wherein the interactive voice response to conditions that are detected and that according to a probabilistic computation are likely to reduce accuracy of an associated speech recognition engine.

10. The system of claim 1, wherein the interactive voice response component automatically returns to a normal mode from a marker mode in response to improved accuracy of an associated speech recognition engine relative to the background noise.

11. A computer-implemented voice response communications system, comprising:

an interactive voice response component for sending message prompts and receiving voice signals via an in-band channel; and

an in-band signaling component for inputting an in-band prompt marker signal during a message prompt to interrupt play of the message prompt, and inputting one or more voice marker signals for delineating a voice signal as part of speech recognition processing.

12. The system of claim 11, wherein the prompt marker signal is generated via a vehicle and communicated to the voice response component by way of a mobile device associated with the vehicle.

13. The system of claim 11, wherein the prompt marker signal terminates play of the message prompt and marks start of the voice signal.

14. The system of claim 11, wherein the voice response component sends instructions for further use of available in-band features related to interrupt of message prompts and delineation of voice signals, manually and automatically.

15. A computer-implemented voice response communications system, comprising:

an interactive voice response component for sending message prompts and receiving voice signals via an in-band channel in presence of background noise, the voice signals processed by a speech recognition engine; and

an in-band signaling component for inputting a marker signal in a form of a DTMF signal into the in-band channel to delineate at least one of a starting point of a voice signal or an ending point of a voice signal.

16. The system of claim 15, wherein the interactive voice response component automatically enables processing of the marker signal via the in-band channel in response to the background noise impacting speech recognition accuracy.

17. The system of claim 15, wherein the interactive voice response component automatically switches between a normal mode and a marker mode in response to changes in accuracy of the speech recognition engine in processing the voice signals relative to the background noise.

18. The system of claim 15, wherein the interactive voice response component automatically sends an instruction for how to input the marker signal.

19. The system of claim 18, wherein the interactive voice response component automatically sends the instruction in response to reduced accuracy of an associated speech recognition engine due to the background noise.

20. A computer-implemented method of voice response communications, comprising:

sending a message prompt via an in-band communications channel;

receiving voice signals in combination with background noise via the in-band communications channel; and

receiving one or more marker signals via the in-band channel relative to at least one of the message prompt or the voice signals, the one or more marker signals relative to the voice signals to delineate the voice signals in presence of the background noise.

21. The method of claim 20, further comprising entering a marker mode based on receipt of a marker signal and processing voice signals received after the marker signal.

22. The method of claim 20, further comprising automatically entering a marker mode and sending an instruction to a source of the voice signals to input a marker signal for further communications.

23. The method of claim 20, further comprising inputting a marker signal to designate at least one of a starting point of the voice signals or an ending point of the voice signals.

24. The method of claim 20, further comprising activating a DTMF signal in response to sending a marker signal.

25. The method of claim 20, further comprising switching between a marker mode and a normal mode based on recognition accuracy of the voice signals relative to the background noise.

26. The method of claim 20, further comprising interrupting play of the message prompt when receiving a marker signal during play of the message prompt.

27. The method of claim 20, further comprising receiving a marker signal generated via a vehicle by way of a mobile device associated with the vehicle.