Automatically providing a user with substitutes for potentially ambiguous user-defined speech commands

• US 8,099,287 B2
• Filed: 12/05/2006
• Issued: 01/17/2012
• Est. Priority Date: 12/05/2006
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Bodin, William K., Lewis, James R., Wilson, Leslie R.
• Primary Examiner(s): Rider, Justin
• Application Number:
  US11/567,084
• Publication Number:
  US 20080133244A1
• Time in Patent Office: 1,869 Days
• Field of Search: None
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method for alleviating ambiguity issues of new user defined speech commands. An original command for a user-defined speech command can be received. It can then be determined if the original command is likely to be confused with a set of existing speech commands. When confusion is unlikely, the original command can be automatically stored. When confusion is likely, a substitute command that is unlikely to be confused with existing commands can be automatically determined. The substitute can be presented as an alternative to the original command and can be selectively stored as the user-defined speech command.

Claims

1. A method comprising:

operating at least one processor programmed to perform

receiving an original command for a user-defined speech command;

determining whether the original command is likely to be confused with a set of existing speech commands;

when confusion is unlikely, automatically storing the original command as the user-defined speech command; and

when confusion is likely, automatically determining at least one substitute command that is unlikely to be confused with the set, presenting the substitute command as an alternative to the original command, and selectively storing the substitute command as the user-defined speech command.

2. The method of claim 1, wherein the substitute command is an automatically determined synonym for the original command.

3. The method of claim 1, wherein the selectively storing step is based upon a user response to the presenting of the substitute command, wherein when the user response indicates a preference to use the original command, the original command is stored as the user-defined speech command.

4. The method of claim 3, wherein when the user response indicates a preference to use the original command, the substitute command is stored as a secondary command for the user-defined speech command, wherein both the original command and the substitute command are able to be used to initiate a set of actions associated with the user-defined speech command.

5. The method of claim 4, wherein the at least one processor is further programmed to perform:

when presenting a prompt relating to the user-defined speech command, presenting the substitute as a trigger for the user-defined speech command instead of presenting the original command.

6. The method of claim 1, wherein the at least one processor is further programmed to perform:

establishing a configurable confusion threshold, wherein a likelihood of whether the original command is confusing with at least one command in the set is based upon whether the confusion threshold is exceeded.

7. The method of claim 1, wherein the likelihood of whether the original command is confusing with at least one command in the set is based upon a determined acoustic similarity between the original command and the at least one command.

8. The method of claim 1, wherein operating the at least one processor to perform the receiving, determining, automatically storing, automatically determining, presenting, and selectively storing comprises operating the at least one processor in accordance with at least one computer program having a plurality of code sections that are executable by the at least one processor.

9. The method of claim 1, wherein the steps of claim 1 are performed by at least one of a service agent and a computing device, comprising the at least one processor, manipulated by the service agents, the steps being performed in response to a service request.

10. A method comprising:

operating at least one processor programmed to perform

ascertaining that an utterance to be associated with a user-defined speech command is acoustically similar to an existing speech command;

automatically determining at least one substitute for the utterance; and

presenting the substitute as an alternative to the utterance.

11. The method of claim 10, wherein the at least one processor is further programmed to perform:

receiving a user acceptance of the substitute; and

adding the substitute to a speech recognition grammar as the user-defined speech command.

12. The method of claim 10, wherein the user-defined speech command is associated with at least one programmatic action, and

wherein the at least one processor is further programmed to perform:

receiving a speech segment from a user;

determining that the speech segment includes the substitute; and

automatically initiating the at least one programmatic action based on the determining step.

13. The method of claim 10, wherein the determining step further comprises:

automatically determining a synonym for the utterance, wherein the substitute is the synonym.

14. The method of claim 10, wherein the at least one substitute comprises a plurality of substitutes, which are each presented in the presenting step.

15. The method of claim 10, wherein the at least one substitute comprises a first substitute and a second substitute, said determining step further comprises:

automatically determining the first substitute;

ascertaining that the first substitute is acoustically similar to an existing speech command;

automatically determining the second substitute; and

ascertaining that the second substitute is not acoustically similar to an existing speech command, wherein the second substitute is the substitute presented in the presenting step.

16. The method of claim 10, wherein the at least one processor is further programmed to perform:

establishing a configurable similarity threshold, wherein the ascertaining step is based upon the similarity threshold.

17. The method of claim 10, wherein the at least one processor is further programmed to perform:

receiving a user denial of the substitute and a user selection of the utterance; and

adding the utterance to a speech recognition grammar as the user-defined speech command.

18. The method of claim 17, wherein the at least one processor is further programmed to perform:

adding the substitute to a speech recognition grammar as an alternative mechanism for initializing the user-defined speech command.

19. The method of claim 18, when presenting a prompt relating to the user-defined speech command, presenting the substitute as a mechanism for initiating the user-defined speech command instead of presenting the original command.

20. A speech processing system comprising:

at least one processor;

at least one speech recognition grammar including at least one user-defined command;

a command execution engine configured to initiate a set of programmatic actions upon detection of user utterance of the user-defined command;

an ambiguity detection engine configured to detect a potential ambiguity between a user provided command and a set of previously established speech commands;

a synonym data store comprising at least one synonym for the user provided command; and

a speech processing engine configured to automatically present a user with the at least one synonym to associate with a new user-defined command, wherever a user provided command for the new user-defined command is determined to be ambiguous by the ambiguity detection engine.