System and method for determining utterance context in a multi-context speech application

• US 7,085,723 B2
• Filed: 08/16/2001
• Issued: 08/01/2006
• Est. Priority Date: 01/12/2001
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Ross, Steven I., Armes, Robert C.
• Primary Examiner(s): Young, Wayne
• Assistant Examiner(s): Wozniak, James S.
• Application Number:
  US09/931,505
• Publication Number:
  US 20020133354A1
• Time in Patent Office: 1,811 Days
• Field of Search: 704/275, 704/270, 704/236, 704/9, 704/251, 704/257, 704/271, 715/728
• US Class Current: 704/275
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A speech center coordinates speech services for a number of speech-enabled applications performing on a computer system. The speech center includes a conversation manager that manages conversations between a user and the speech-enabled applications. The conversation manager includes a context manager that maintains a context list of speech-enabled applications that the user has accessed. If the user speaks an utterance, the context manager determines which speech-enabled application should receive a translation of the utterance from the context list, such as by determining the most recently accessed application.

Claims

1. A method for determining a speech-enabled application to receive a spoken utterance in a multi-context speech enabled environment comprising the computer implemented steps of:

evaluating a plurality of contexts for speech enabled applications and prioritizing the contexts based upon a recency of relevant access characteristic, said evaluating being based upon different grammars maintained for each speech enabled application comprising persistent, foreground, and background grammars, and said evaluating being applied to speech enabled applications whether the application is running or not;

receiving a representation of a spoken utterance, the spoken utterance including a command that is able to be associated with multiple applications, any subset of which may or may not be running; and

directing the representation of the spoken utterance to a selected speech enabled application based upon results of the step of evaluating the contexts, wherein the command is applied to the selected speech enabled application including launching the selected speech enabled application as needed and performing function of the command.

2. The method of claim 1, further comprising the step, prior to evaluating the contexts, of creating the contexts for the speech enabled applications in the speech enabled environment.

3. The method of claim 1 further comprising the step of identifying each context based on a persistent grammar, a foreground grammar, or a background grammar for each speech enabled application.

4. The method of claim 1, wherein the step of directing the representation of the spoken utterance comprises using a grammar to identify and select a context of the selected speech enabled application.

5. The method of claim 4, wherein the grammar is a Backus Naur Form grammar.

6. Computer apparatus for determining a speech-enabled application to receive a spoken utterance in a multi-context speech enabled environment, comprising:

a context manager for evaluating a plurality of contexts for speech enabled applications and prioritizing the contexts based upon a recency of relevant access characteristic, said context manager evaluating a context based on distinct grammars maintained for each speech enabled application comprising persistent, foreground, and background grammars, and said context manager evaluating each speech enabled application whether the application is running or not; and

a message handler for receiving a representation of a spoken utterance, the spoken utterance including a command that is able to be associated with multiple applications, any subset of which may or may not be running;

the context manager receiving the representation of the spoken utterance from the message handler and directing the representation of the spoken utterance to a selected speech enabled application based upon the evaluating of the contexts, wherein the command is applied to the selected speech enabled application including launching the selected speech enabled application as needed and performing function of the command.

7. The apparatus of claim 6, wherein the context manager, prior to evaluating the contexts, creates the contexts for the speech enabled applications in the speech enabled environment.

8. The apparatus of claim 6, wherein the context manager identifies each context based on a persistent grammar, a foreground grammar, or a background grammar for each speech enabled application.

9. The apparatus of claim 6, wherein the context manager uses a grammar to identify the selected speech enabled application.

10. The apparatus of claim 9, wherein the grammar is a Backus Naur Form grammar.

11. A computer program product comprising:

a computer usable medium for determining a speech-enabled application to receive a spoken utterance in a multi-context speech enabled environment; and

a set of computer program instructions embodied on the computer useable medium, including instructions to;

evaluate contexts for speech enabled applications and prioritize the contexts based upon a recency of relevant access characteristic, regardless of the speech enabled applications'"'"' running state, said evaluating being based upon distinct grammars maintained for each speech enabled application comprising persistent, foreground, and background grammars;

receive a representation of a spoken utterance, the spoken utterance including a command that is able to be associated with multiple applications, any subset of which may or may not be running; and

direct the representation of the spoken utterance to a selected speech enabled application based upon the evaluation of the contexts, wherein the command is applied to the selected speech enabled application including launching the selected speech enabled application as needed and performing function of the command.

12. The computer program product of claim 11, wherein the set of computer instructions comprises further instructions, prior to evaluating the contexts, to create the contexts for the speech enabled applications in the speech enabled environment.

13. The computer program product of claim 11, wherein the set of computer instructions comprises further instructions to identify each context based on a persistent grammar, a foreground grammar, or a background grammar for each speech enabled application.

14. The computer program product of claim 11, wherein the set of computer instructions comprises further instructions to use a grammar to identify the selected speech enabled application.

15. The computer program product of claim 14, wherein the grammar is a Backus Naur Form grammar.

16. A computer implemented method for determining a speech-enabled application to receive a spoken utterance in a multi-context speech enabled environment comprising the steps of:

evaluating a plurality of contexts for speech enabled applications and prioritizing the contexts based upon a recency of relevant access characteristic, said evaluating being based upon distinct grammars maintained for each speech enabled application comprising persistent, foreground, and background grammars;

receiving a representation of a spoken utterance, the spoken utterance including a command that is able to be associated with multiple approaches; and

directing the representation of the spoken utterance to a selected speech enabled application based upon results of the step of evaluating the contexts, wherein the command is applied to the selected speech enabled application including launching the selected speech enabled application as needed and performing function of the command.

17. A method as claimed in claim 16 wherein said directing is biased to the most recently accessed application.