AUTOMATICALLY PROVIDING A USER WITH SUBSTITUTES FOR POTENTIALLY AMBIGUOUS USER-DEFINED SPEECH COMMANDS

• US 20120095765A1
• Filed: 12/22/2011
• Published: 04/19/2012
• Est. Priority Date: 12/05/2006
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Bodin, William K., Lewis, James R., Wilson, Leslie R.
• Granted Patent: US 8,380,514 B2
• Time in Patent Office: Days
• US Class Current: 704/251
• 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

1-20. -20. (canceled)

21. A method comprising:

performing a speech recognition process on a first speech input to determine whether at least a portion of the first speech input potentially matches any of a plurality of voice commands; and

when it is determined, based on the speech recognition process, that the at least a portion of the first speech input potentially matches at least a first voice command and a second voice command of the plurality of voice commands,

attempting to identify a synonym for at least one word of the first voice command, and

when the synonym is identified, prompting a user to provide a second speech input including the synonym if the user intended to invoke the first voice command by speaking the first speech input.

22. The method of claim 21, wherein performing the speech recognition process to determine whether the at least a portion of the first speech input potentially matches any of the plurality of voice commands comprises determining whether an entirety of the first speech input potentially matches any of the plurality of voice commands.

23. The method of claim 21, wherein attempting to identify the synonym comprises identifying the synonym, and

wherein prompting the user when the synonym is identified comprises prompting the user to provide the second speech input including the synonym if the user intended to invoke the first voice command.

24. The method of claim 21, further comprising, when the synonym for the at least one word of the first voice command is identified, substituting the at least one word of the first voice command with the synonym to create a substitute expression,

wherein prompting the user to provide the second speech input including the synonym comprises prompting the user to provide the second speech input including the substitute expression if the user intended to invoke the first voice command by speaking the first speech input.

25. The method of claim 21, wherein performing the speech recognition process on the first speech input comprises evaluating the first speech input based at least in part on a voice command grammar, the voice command grammar comprising voice commands that can be used to trigger a computer system to perform one or more actions associated with the voice commands.

26. The method of claim 21, wherein attempting to identify the synonym for the first voice command comprises retrieving, for the first voice command, a previously-stored alternative voice command associated with the first voice command, the previously-stored alternative voice command comprising the synonym.

27. The method of claim 26, further comprising, prior to performing the speech recognition process, creating the previously-stored alternative voice command, the creating comprising:

receiving a request from a user to add a new voice command to a voice command grammar, the new voice command comprising the first voice command;

searching a data store of synonyms based on the first voice command to determine the synonym;

adding the synonym to the voice command grammar and associating the synonym with the first voice command as an alternative to the first voice command.

28. The method of claim 21, wherein the first voice command is a single word and attempting to identify the synonym for the at least one word of the first voice command comprises attempting to identify a synonym for the single word of the first voice command.

29. The method of claim 21, wherein the first voice command is a phrase comprising two or more words and attempting to identify the synonym for the at least one word of the first voice command comprises attempting to identify a synonym for the phrase.

30. The method of claim 21, further comprising:

when it is determined that the at least a portion of the first speech input potentially matches at least the first voice command and the second voice command, attempting to identify a synonym for the second voice command, and

when synonyms are identified for the first voice command and the second voice command, further prompting the user to provide a second speech input including the synonym identified for the second voice command if the user intended to invoke the second voice command by speaking the first speech input.

31. The method of claim 30, wherein prompting the user to provide a second speech input including the synonym identified for the first voice command and prompting the user to provide a second speech input including the synonym identified for the second voice command comprises prompting the user with the same prompt.

32. At least one computer-readable storage medium having encoded thereon processor-executable instructions that, when executed by at least one processor, cause the at least one processor to carry out a method, the method comprising:

performing a speech recognition process on a first speech input to determine whether at least a portion of the first speech input potentially matches any of a plurality of voice commands; and

when it is determined, based on the speech recognition process, that the at least a portion of the first speech input potentially matches at least a first voice command and a second voice command of the plurality of voice commands,

attempting to identify a synonym for at least one word of the first voice command, and

when the synonym is identified, prompting a user to provide a second speech input including the synonym if the user intended to invoke the first voice command by speaking the first speech input.

33. The at least one computer-readable storage medium of claim 32, wherein attempting to identify the synonym for the first voice command comprises retrieving, for the first voice command, a previously-stored alternative voice command associated with the first voice command, the previously-stored alternative voice command comprising the synonym.

34. The at least one computer-readable storage medium of claim 32, wherein attempting to identify the synonym for the at least one word of the first voice command comprises attempting to identify a synonym for the first voice command.

35. The at least one computer-readable storage medium of claim 32, wherein the method further comprises:

when it is determined that the at least a portion of the first speech input potentially matches at least the first voice command and the second voice command, attempting to identify a synonym for the second voice command, and

when synonyms are identified for the first voice command and the second voice command, further prompting the user to provide a second speech input including the synonym determined for the second voice command if the user intended to invoke the second voice command by speaking the first speech input.

36. An apparatus comprising:

at least one processor; and

at least one computer-readable storage medium accessible by the at least one processor and having encoded thereon processor-executable instructions that, when executed by the at least one processor, cause the at least one processor to carry out a method, the method comprising;

performing a speech recognition process on a first speech input to determine whether at least a portion of the first speech input potentially matches any of a plurality of voice commands; and

when it is determined, based on the speech recognition process, that the at least a portion of the first speech input potentially matches at least a first voice command and a second voice command of the plurality of voice commands,

attempting to identify a synonym for at least one word of the first voice command, and

when the synonym is identified, prompting a user to provide a second speech input including the synonym if the user intended to invoke the first voice command by speaking the first speech input.

37. The apparatus of claim 36, wherein performing the speech recognition process on the first speech input comprises evaluating the first speech input based at least in part on a voice command grammar, the voice command grammar comprising voice commands that can be used to trigger a computer system to perform one or more actions associated with the voice commands.

38. The apparatus of claim 36, wherein attempting to identify the synonym for the first voice command comprises retrieving, for the first voice command, a previously-stored alternative voice command associated with the first voice command, the previously-stored alternative voice command comprising the synonym.

39. The apparatus of claim 36, wherein attempting to identify the synonym comprises identifying the synonym, and

wherein prompting the user when the synonym is identified comprises prompting the user with to provide the second speech input including the synonym if the user intended to invoke the first voice command.

40. The apparatus of claim 36, wherein attempting to identify the synonym for the at least one word of the first voice command comprises attempting to identify a synonym for the first voice command.