Multi-context conversational environment system and method

• US 6,944,594 B2
• Filed: 05/30/2001
• Issued: 09/13/2005
• Est. Priority Date: 05/30/2001
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Bellsouth Intellectual Property Corporation (AT&T, Inc.)
• Inventors: Busayapongchai, Senis, Chintrakulchai, Pichet
• Primary Examiner(s): Ometz, David L.
• Assistant Examiner(s): Wozniak, James S.
• Application Number:
  US09/870,202
• Publication Number:
  US 20020184023A1
• Time in Patent Office: 1,567 Days
• Field of Search: 704/275, 704/270, 704/270.1, 704/251, 379/907, 379/917
• US Class Current: 704/275
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

An interactive speech-activated information retrieval application for use in automated telephone systems includes a control manager that interfaces between the caller'"'"'s speech input and applications and enables several applications to be open at the same time. The control manager continually monitors for control words, enabling the user to switch between applications at will. When a user switches to another application, the control manager suspends the first application and stores its context, enabling the user to later return to the application at the point where the application was previously suspended.

Claims

1. A method of speech recognition processing that provides audible information over a communications device comprising:

receiving a first speech input at a network server, said first speech input associated with a caller menu system and indicative of a first subject area;

initiating a first subject application associated with said first subject area;

receiving a second speech input at the network server, said second speech input associated with the caller menu system, said second speech input indicative of a second subject area associated with a second independent application;

storing at least one indicator indicating a current processing step of said first subject application; and

storing a current context associated with said first speech input associated with said first subject application in a context table and audibly outputting said current context upon a user request.

2. The method according to claim 1, further comprising initiating said second subject application associated with said second subject area.

3. The method according to claim 1, further comprising initiating a task agent for said first subject application.

4. The method according to claim 1, further comprising monitoring said first speech input for at least one word indicative of said second subject area.

5. The method according to claim 1, further comprising suspending said first subject application after receiving said second speech input.

6. The method according to claim 5, further comprising:

receiving a further speech input, and re-activating said first subject application responsive to the further speech input.

7. The method according to claim 1, wherein said storing at least one indicator further comprises storing a series of indicators that indicate a processing path of said first application.

8. The method according to claim 7, further comprising outputting a computer-generated representation of said stored series of indicators that indicates said processing path of said first application.

9. The method according to claim 1, further comprising outputting information associated with said first application in a first voice.

10. The method according to claim 9, further comprising outputting information associated with a second application in a second voice, said second voice being distinguishable from said first voice.

11. The method according to claim 1, further comprising synthesizing speech for outputting speech from said first application.

12. A speech recognition system comprising:

a speech recognition module located at a network server that processes speech input and translates said speech input into computer-readable input;

a control manager comprising;

a module that interfaces between said speech input and at least one of a plurality of caller menu application programs;

a module that initiates processing of a first application program; and

a module that monitors said speech input for a request to initiate a second independent application program;

a module that stores a current context of said first application program in a context table and audibly outputs said current context upon a user request; and

a speech synthesizing module for providing output information from said plurality of application programs.

13. The system according to claim 12, wherein the context table maintains a first current context for said first application program and a second current context for said second application.

14. The system according to claim 12, further comprising a plurality of task agents, each task agent associated with one of said plurality of application programs.

15. The system according to claim 14, wherein the control manager is adapted to assign said application programs to said task agents, and switch control among said task agents.

16. The system according to claim 12, wherein the request comprises a control word.

17. The system according to claim 12, wherein the control manager is adapted to suspend said first application program, and initiate processing of said second application program, responsive to the request.

18. The system according to claim 17, wherein the control manager is adapted to re-activate said first application program responsive to a further request.

19. The system according to claim 12, wherein the control manager is adapted to store at least one indicator indicative of a current processing step of at least one of said plurality of application programs.

20. A computer-readable medium for storing computer-executable instructions for:

receiving a first speech input at a network server, said first speech input associated with a caller menu system and indicative of a first subject area;

initiating a first subject application associated with said first subject area;

receiving a second speech input at the network server, said second speech input associated with the caller menu system, said second speech input indicative of a second subject area associated with a second independent application;

storing at least one indicator indicating a current processing step of said first subject application; and

storing a current context associated with said first speech input associated with said first subject application in a context table and audibly outputting said current context upon a user request.