Establishing call-based audio sockets within a componentized voice server

• US 8,019,607 B2
• Filed: 07/31/2008
• Issued: 09/13/2011
• Est. Priority Date: 04/28/2004
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Creamer, Thomas E., Moore, Victor S., Nusbickel, Wendi L., Sliwa, James J., Dos Santos, Ricardo
• Primary Examiner(s): McFadden; Susan
• Application Number:
  US12/183,639
• Publication Number:
  US 20090055191A1
• Time in Patent Office: 1,139 Days
• Field of Search: 704/270.1, 379/88.14
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems

Abstract

A method of interfacing a telephone application server and a speech engine can include the step of establishing one or more audio sockets in a media converting component of the telephone application server. The audio socket can remain available for approximately a duration of a call. A work unit that requires processing by a speech engine can be detected for the call. An identifier for the audio socket and a data for the work unit can be conveyed to a selected speech engine. Work unit results from the selected speech engine can be received by the media converting component via the previously established audio socket.

Claims

1. A system for establishing call-based audio sockets within a componentized voice server for communicating with external speech engines, the system comprising:

hardware means for receiving a call via a telephone gateway;

means for initializing the voice server to handle the call;

means for establishing at least one audio socket in a media converting component of the voice server for interfacing the voice server with an external speech engine, the at least one audio socket remaining available for approximately a duration of the call;

means for detecting a work unit of said call that requires processing by an external speech engine;

means for conveying an identifier for the at least one audio socket and data relating to the work unit to a selected external speech engine; and

means for receiving work unit results from the selected external speech engine via the at least one audio socket.

2. The system of claim 1, wherein said external speech engine communicates to said telephone gateway using said media converting component as an intermediary, and wherein said external speech engine connects to said telephone gateway via audio sockets established by the media converting component, said established audio sockets being associated with selected telephone calls, and wherein said audio sockets remain available for approximately the duration of the associated telephone call.

3. The system of claim 2, wherein different external speech engines convey work unit results via a single one of said audio sockets during a telephone call for which the audio socket was established.

4. 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:

receiving a call;

initializing a voice server to handle the call;

establishing at least one audio socket in a media converting component of the voice server for interfacing the voice server with an external speech engine, said at least one audio socket remaining available for approximately a duration of the call;

detecting a work unit of said call that requires processing by an external speech engine;

conveying an identifier for the audio socket and data relating to the work unit to a selected external speech engine; and

receiving work unit results from the selected external speech engine via the at least one audio socket.

5. The machine-readable storage of claim 4, further comprising the steps of:

after the work unit data is processed, the external speech engine initializing a communication connection with the audio socket; and

responsive to said initialization, conveying pending audio signals from the media converting component to the audio socket.

6. The machine-readable storage of claim 4, further comprising the steps of:

detecting a different work unit of said call that requires processing by a speech engine;

conveying said identifier for the audio socket and conveying data relating to the different work unit to a different external speech engine; and

receiving work unit results from said different external speech engine via the same audio socket.

7. The machine-readable storage of claim 6, wherein said external speech engine is an automatic speech recognition engine and wherein said different external speech engine is a text-to-speech engine.

8. The machine-readable storage of claim 4, wherein said at least one audio socket is a plurality of audio sockets.

9. The machine-readable storage of claim 8, wherein said plurality of audio sockets comprises at least one input audio socket and at least one output audio socket.

10. The machine-readable storage of claim 4, wherein said voice server has a componentized architecture of different modular components, wherein each component within said architecture is configured to handle tasks in a functionally isolated fashion from other components of said architecture.

11. A system for establishing call-based audio sockets within a voice server for communicating with speech engines, the system comprising:

at least one input for receiving a call from a telephone gateway; and

at least one computer capable of processing the call received from the at least one input, the at least one computer configured to implement;

initializing the voice server to handle the call;

establishing at least one audio socket in a media converting component of the voice server for interfacing the voice server with at least one speech engine, the at least one audio socket remaining available for approximately a duration of the call;

detecting a work unit of the call that requires processing by a speech engine from the at least one speech engine;

conveying an identifier for the at least one audio socket and data relating to the work unit to the speech engine; and

receiving work unit results from the speech engine via the at least one audio socket.

12. The system of claim 11, wherein:

the speech engine communicates with the telephone gateway using the media converting component as an intermediary,

the speech engine connects to the telephone gateway via audio sockets established by the media converting component, the established audio sockets being associated with selected telephone calls, and

the audio sockets remain available for approximately the duration of the associated telephone call.

13. The system of claim 12, wherein different speech engines convey work unit results via one audio socket of the audio sockets during a telephone call for which the audio socket was established.