Barge-in capabilities of a voice browser

• US 8,229,750 B2
• Filed: 04/28/2004
• Issued: 07/24/2012
• Est. Priority Date: 04/28/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Creamer, Thomas E., Moore, Victor S., Nusbickel, Wendi L., Dos Santos, Ricardo, Sliwa, James J.
• Primary Examiner(s): Armstrong, Angela A
• Application Number:
  US10/833,518
• Publication Number:
  US 20050246173A1
• Time in Patent Office: 3,009 Days
• Field of Search: 704/270, 704/270.1
• US Class Current: 704/270
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A method for barging-in a call can include the step of establishing a component as a communication intermediary between at least one speech engine and a telephone gateway. The component can include at least one input media port and at least one output media port, where the input media port and the output media port can interface with selective ones of the speech engines. A barge-in command can be received while an automated prompt is being audibly presented. The signals for the prompt can be conveyed to the component via the output media port. Once the barge-in command has been received, the output media port can be closed to immediately stop the prompt from being presented. A halt command can be conveyed to a prompt generating source so that the source stops generating the prompt.

Claims

1. A computer-implemented system with rapid call-barge-in facilities comprising:

hardware and software configured to implement;

a telephone gateway;

at least one speech engine; and

a voice server comprising hardware and having a plurality of modular components, wherein one component of the plurality of modular components is a media converting component configured as a communication intermediary between the telephone gateway and the at least one speech engine, wherein the media converting component comprises an output media port via which communications are sent from the at least one speech engine to the telephone gateway, and wherein the media converting component is configured to close the output media port responsive to detecting a barge-in condition.

2. The system of claim 1, wherein the at least one speech engine comprises a first speech engine, and wherein the system further comprises a second speech engine, and wherein the media converting component is configured as a communication intermediary between the telephone gateway and the first speech engine and between the telephone gateway and the second speech engine.

3. The system of claim 2, wherein the media converting component further comprises an input media port via which communications are sent from the telephone gateway to the second speech engine.

4. The system of claim 3, wherein the input media port and the output media port provide communication links for a same telephone call, and wherein the input media port and the output media port remain allocated to the telephone call for approximately a duration of the telephone call.

5. The system of claim 3, wherein the first speech engine comprises at least one text-to-speech engine configured to convey generated speech to the telephone gateway through the output media port, and wherein the second speech engine comprises at least one automatic speech recognition engine configured to receive speech utterances from the telephone gateway through the input media port during playback of speech generated by the at least one text-to-speech engine, wherein the at least one automatic speech recognition engine is configured to determine that particular speech utterances represent barge-in conditions.

6. The system of claim 3, wherein the media converting component further comprises a control port for conveying control signals between the first speech engine, the second speech engine, and the media converting component, one control signal being a halt command for ending a presentation of an audio prompt provided by one of the first and second speech engines.

7. A computer-implemented method for use in a system comprising a component configured as a communication intermediary between a telephone gateway and at least one speech engine, the component having an output media port via which communications are sent from the at least one speech engine to the telephone gateway, the method comprising:

detecting a barge-in condition while an automated prompt is being audibly presented via the telephone gateway, wherein signals corresponding to the prompt are conveyed to the component via the output media port;

closing, responsive to the detecting step, the output media port to immediately stop the prompt from being presented; and

conveying a halt command to a prompt generating source to stop the prompt generating source from generating the prompt.

8. The method of claim 7, wherein the output media port remains closed until the audible presentation of the prompt has completed.

9. The method of claim 7, wherein the component is a media converting component.

10. The method of claim 7, wherein the at least one speech engine comprises a text-to-speech engine that conveys at least one of generated speech and prerecorded audio signals to the component via the output media port, the text-to-speech engine being the prompt generating source.

11. The method of claim 7, wherein the system further comprises an automatic speech recognition engine and wherein the component further has an input media port via which communications are sent from the telephone gateway to the automatic speech recognition engine, the method further comprising:

receiving a speech utterance from the telephone gateway;

conveying the speech utterance to the automatic speech recognition engine via the input media port;

converting the speech utterance to text; and

determining the barge-in condition from the text.

12. The method of claim 7, further comprising:

receiving an in-band, non-speech signal from the telephone gateway; and

interpreting the in-band, non-speech signal as the barge-in condition.

13. The method of claim 7, further comprising associating the output media port with a telephone call, wherein the output media port remains allocated to the telephone call for approximately a duration of the telephone call.

14. The method of claim 7, wherein the at least one speech engine comprises a first speech engine and wherein the system further comprises a second speech engine, the component having an input media port via which communications are sent from the telephone gateway to the second speech engine, wherein at least one of the input media port and the output media port is utilized by a plurality of different speech engines during a telephone call, each speech engine of the plurality of different speech engines processing a selected work unit relating to the telephone call, the work unit being determined by a voice server, the component being a subcomponent of the voice server.

15. The method of claim 7, wherein the component further comprises a control port, and wherein the method further comprises:

establishing a communication link between the component and the at least one speech engine via the control port; and

conveying control signals across the control port, wherein the halt command is one of the control signals.

16. A machine-readable storage having stored thereon a computer program having a plurality of code sections, the plurality of code sections executable by a machine to cause a system to perform a method, the system comprising a component configured as a communication intermediary between a telephone gateway and at least one speech engine, the component having an output media port via which communications are sent from the at least one speech engine to the telephone gateway, the method comprising:

detecting a barge-in condition while an automated prompt is being audibly presented via the telephone gateway, wherein signals corresponding to the prompt are conveyed to the component via the output media port;

closing, responsive to the detecting step, the output media port to immediately stop the prompt from being presented; and

conveying a halt command to a prompt generating source to stop the prompt generating source from generating the prompt, wherein the output media port remains closed until the audible presentation of the prompt has completed.

17. The machine-readable storage of claim 16, wherein the component is a media converting component.

18. The machine-readable storage of claim 16, wherein the at least one speech engine comprises a text-to-speech engine that conveys at least one of generated speech and prerecorded audio signals to the component via the output media port, the text-to-speech engine being the prompt generating source.

19. The machine-readable storage of claim 16, wherein the system further comprises an automatic speech recognition engine and wherein the component further has an input media port via which communications are sent from the telephone gateway to the automatic speech recognition engine, and wherein the method further comprises:

receiving a speech utterance from the telephone gateway;

conveying the speech utterance to the automatic speech recognition engine via the input media port;

converting the speech utterance to text; and

determining the barge-in condition from the text.

20. The machine-readable storage of claim 16, wherein the method further comprises:

receiving an in-band, non-speech signal from the telephone gateway; and

interpreting the in-band, non-speech signal as the barge-in condition.

21. The machine-readable storage of claim 16, wherein the method further comprises associating the output media port with a telephone call, wherein the output media port remains allocated for approximately a duration of the telephone call.

22. The machine-readable storage of claim 16, wherein the component further comprises a control port, and wherein the method further comprises:

establishing a communication link between the component and the at least one speech engine via the control port; and

conveying control signals across the control port, wherein the halt command is one of the control signals.