SYSTEMS AND METHODS FOR RESPONDING TO NATURAL LANGUAGE SPEECH UTTERANCE

• US 20130297293A1
• Filed: 11/30/2012
• Published: 11/07/2013
• Est. Priority Date: 08/05/2005
• Status: Active Grant

• Current Assignee: Dialect, LLC
• Original Assignee: VoiceBox Technologies, Inc. (Microsoft Corporation)
• Inventors: Di Cristo, Philippe, Ke, Min, Kennewick, Robert A., Armstrong, Lynn Elise
• Granted Patent: US 8,849,670 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.

Claims

1-30. -30. (canceled)

31. A system for facilitating notification of context changes across multiple electronic devices, the system including one or more processors executing one or more computer program modules which, when executed, cause the system to:

register a library associated with a first electronic device to subscribe the first electronic device to one or more context events;

receive a context change event from a second electronic device; and

inform the first electronic device of the context change event to synchronize a context across the first electronic device and the second electronic device.

32. The system of claim 31, wherein the system is caused to:

receive a subsequent context change event from the first electronic device; and

inform the second electronic device of the subsequent context change event in response to the second electronic device having a subscription to the subsequent context change event.

33. The system of claim 31, wherein the system is caused to remove the library to unsubscribe the first electronic device from the one or more context events.

34. A method for facilitating notification of context changes across multiple electronic devices, the method being implemented in a computer system that includes one or more processors executing one or more computer program modules which, when executed, perform the method, the method comprising:

registering a library associated with a first electronic device to subscribe the first electronic device to one or more context events;

receiving a context change event from a second electronic device; and

informing the first electronic device of the context change event to synchronize a context across the first electronic device and the second electronic device.

35. The method of claim 34, further comprising:

receiving a subsequent context change event from the first electronic device; and

informing the second electronic device of the subsequent context change event in response to the second electronic device having a subscription to the subsequent context change event.

36. The method of claim 34, further comprising removing the library to unsubscribe the first electronic device from the one or more context events.

37. A system for facilitating context-based speech recognition, the system including one or more processors executing one or more computer program modules which, when executed, cause the system to:

access one or more contexts that are stored in a context stack associated with a natural language utterance in response to one or more grammars in a context description grammar failing to correspond to information associated with the natural language utterance;

compare the information to one or more context matchers to determine a most likely context associated with the natural language utterance; and

use one or more grammar expression entries in the context description grammar to generate a command or request associated with the most likely context.

38. The system of claim 37, wherein the system is caused to communicate the generated command or request to an agent configured to process the generated command or request in the most likely context and generate a response to the natural language utterance.

39. The system of claim 37, wherein the system is caused to determine an intent or correct a recognition associated with the natural language utterance based on the most likely context.

40. The system of claim 37, wherein the system is caused to dynamically constrain a vocabulary of words associated with a virtual dictation grammar to include one or more decoy words for out-of-vocabulary words based on one or more prior utterances that were successfully transcribed by the speech recognition engine.

41. The system of claim 37, wherein the system is caused to use a dictation grammar or a virtual dictation grammar to completely or partially transcribe the natural language utterance.

42. A method for facilitating context-based speech recognition, the method being implemented in a computer system that includes one or more processors executing one or more computer program modules which, when executed, perform the method, the method comprising:

accessing one or more contexts that are stored in a context stack associated with a natural language utterance in response to one or more grammars in a context description grammar failing to correspond to information associated with the natural language utterance;

comparing the information to one or more context matchers to determine a most likely context associated with the natural language utterance; and

using one or more grammar expression entries in the context description grammar to generate a command or request associated with the most likely context.

43. The method of claim 42, further comprising communicating the generated command or request to an agent configured to process the generated command or request in the most likely context and generate a response to the natural language utterance.

44. The method of claim 42, further comprising determining an intent or correct a recognition associated with the natural language utterance based on the most likely context.

45. The method of claim 42, further comprising dynamically constraining a vocabulary of words associated with a virtual dictation grammar to include one or more decoy words for out-of-vocabulary words based on one or more prior utterances that were successfully transcribed by the speech recognition engine.

46. The method of claim 42, further comprising using a dictation grammar or a virtual dictation grammar to completely or partially transcribe the natural language utterance.

47. A system for facilitating speech recognition using dictation and/or virtual dictation grammars, the system including one or more processors executing one or more computer program modules which, when executed, cause the system to:

receive a natural language utterance; and

transcribe the natural language utterance using a dictation grammar of a speech recognition module or a virtual dictation grammar of the speech recognition module based on whether a platform associated with the speech recognition module has the dictation grammar available.

48. The system of claim 47, wherein the system is caused to dynamically constrain a vocabulary of words associated with the virtual dictation grammar to include one or more decoy words for out-of-vocabulary words based on one or more prior utterances that the speech recognition module successfully transcribed.

49. The system of claim 47, wherein the system is caused to:

identify a context matching a command or request associated with the transcribed natural language utterance;

process, at an agent associated with the identified context, the command or request to generate a response to the natural language utterance; and

update, at the agent, a context stack with information associated with the identified context, the generated command or request, or the generated response to enable one or more follow-up commands or requests associated with the identified context, the generated command or request, or the generated response.

50. The system of claim 47, wherein transcribing the natural language utterance comprises using the dictation grammar or the virtual dictation grammar to completely or partially transcribe the natural language utterance.

51. A method for facilitating speech recognition using dictation and/or virtual dictation grammars, the method being implemented in a computer system that includes one or more processors executing one or more computer program modules which, when executed, perform the method, the method comprising:

receiving a natural language utterance; and

transcribing the natural language utterance using a dictation grammar of a speech recognition module or a virtual dictation grammar of the speech recognition module based on whether a platform associated with the speech recognition module has the dictation grammar available.

52. The method of claim 51, further comprising dynamically constraining a vocabulary of words associated with the virtual dictation grammar to include one or more decoy words for out-of-vocabulary words based on one or more prior utterances that the speech recognition module successfully transcribed.

53. The method of claim 51, further comprising:

identifying a context matching a command or request associated with the transcribed natural language utterance;

processing, at an agent associated with the identified context, the command or request to generate a response to the natural language utterance; and

updating, at the agent, a context stack with information associated with the identified context, the generated command or request, or the generated response to enable one or more follow-up commands or requests associated with the identified context, the generated command or request, or the generated response.

54. The method of claim 51, wherein transcribing the natural language utterance comprises using the dictation grammar or the virtual dictation grammar to completely or partially transcribe the natural language utterance.