Barge-in capabilities of a voice browser

• US 20050246173A1
• Filed: 04/28/2004
• Published: 11/03/2005
• Est. Priority Date: 04/28/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Creamer, Thomas E., Moore, Victor S., Nusbickel, Wendi L., Sliwa, James J., Santos, Ricardo Dos
• Granted Patent: US 8,229,750 B2
• Time in Patent Office: Days
• 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 method for barging-in an audio prompt during a call comprising the steps of:

establishing a component as a communication intermediary between at least one speech engine and a telephone gateway, said component having at least one input media port and at least one output media port, said input media port and said output media port interfacing with selective ones of said speech engines;

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

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

conveying a halt command to a prompt generating source so that said source stops generating said prompt.

2. The method of claim 1, wherein said output media port remains closed until the audible presentation of the prompt has completed.

3. The method of claim 1, wherein said component is a media converting component of a componentized voice server, said media converting component functioning as a communication intermediary between said telephone gateway and said componentized voice server.

4. The method of claim 1, wherein said at least one speech engine comprises a text-to-speech engine that conveys at least one of generated speech and prerecorded audio signals to said component via said output media port, said text-to-speech engine being said prompt generating source.

5. The method of claim 1, wherein said at least one speech engine comprises an automatic speech recognition engine, said method further comprising the steps of:

receiving a speech utterance from said telephone gateway;

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

speech-to-text converting said speech utterance; and

determining said barge-in condition from said converted utterance.

6. The method of claim 1, further comprising the steps of:

receiving an in-band, non-speech signal from said telephone gateway, said signal resulting from a customer premise equipment input; and

interpreting said signal as said barge-in condition.

7. The method of claim 1, further comprising the step of:

associating said input media port and said output media port with a telephone call, wherein said input media port and said output media port remain allocated for approximately a duration of said telephone call.

8. The method of claim 1, wherein at least one of said input media port and said output media port are utilized by a plurality of different speech engines during a telephone call, each speech engine processing a selected work unit relating to said telephone call, said work unit being determined by a voice server, said component being a subcomponent of said voice server.

9. The method of claim 1, said component further comprising at least one control port, said method further comprising the steps of:

establishing a communication link with each of said speech engines and said component via said control port; and

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

10. A machine-readable storage having stored thereon, a computer program having a plurality of code sections, said code sections executable by a machine for causing the machine to perform the steps of:

establishing a component as a communication intermediary between at least one speech engine and a telephone gateway, said component having at least one input media port and at least one output media port, said input media port and said output media port interfacing with selective ones of said speech engines;

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

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

conveying a halt command to a prompt generating source so that said source stops generating said prompt, wherein said output media port remains closed until the audible presentation of the prompt has completed.

11. The machine-readable storage of claim 10, wherein said component is a media converting component of a componentized voice server, said media converting component functioning as a communication intermediary between said telephone gateway and said componentized voice server.

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

13. The machine-readable storage of claim 10, wherein said at least one speech engine comprises an automatic speech recognition engine, said machine-readable storage further comprising the steps of:

receiving a speech utterance from said telephone gateway;

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

speech-to-text converting said speech utterance; and

determining said barge-in condition from said converted utterance.

14. The machine-readable storage of claim 10, further comprising the steps of:

receiving an in-band, non-speech signal from said telephone gateway, said signal resulting from a customer premise equipment input; and

interpreting said signal as said barge-in condition.

15. The machine-readable storage of claim 10, further comprising the step of:

associating said input media port and said output media port with a telephone call, wherein said input media port and said output media port remain allocated for approximately a duration of said telephone call.

16. The machine-readable storage of claim 10, said component further comprising at least one control port, said machine-readable storage further comprising the steps of:

establishing a communication link with each of said speech engines and said component via said control port; and

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

17. A system with rapid call-barge-in facilities comprising:

a telephone gateway;

at least one speech engine; and

a voice server having a componentized architecture of different modular components, wherein one of said components is a media converting component, wherein said media converting component is configured as a communication intermediary between said at least one speech engine and said telephone gateway, and wherein said media converting component comprises at least one input media port and at least one output media port, said input media port and said output media port interfacing with selective ones of said speech engines, and wherein said media converting component is configured to close said at least one output media port responsive to detecting a barge-in condition.

18. The system of claim 17, wherein said input media port and said output media port are associated with a telephone call, and wherein said input media port and said output media port remain allocated for approximately a duration of said telephone call.

19. The system of claim 17, wherein said at least one speech engine comprises at least one text-to-speech engine and at least one automatic speech recognition engine, said text-to-speech engine conveying generated speech to said telephone gateway through said output media port, said automatic speech recognition engine receiving speech utterances from said telephone gateway through said input media port during playback of speech generated by said text-to-speech engine, wherein said automatic speech recognition engine is configured to determine that particular speech utterances represent barge-in conditions,

20. The system of claim 17, wherein said media converting component further comprises:

a control port for conveying control signals between each of the speech engines and the media converting component, one control signal being a halt command for ending a presentation of an audio prompt provided by one of said speech engines.