Mobile systems and methods for responding to natural language speech utterance

• US 20040193420A1
• Filed: 07/15/2003
• Published: 09/30/2004
• Est. Priority Date: 07/15/2002
• Status: Active Grant

• Current Assignee: Dialect, LLC
• Original Assignee: VoiceBox Technologies Corporation (Microsoft Corporation)
• Inventors: Kennewick, Robert A., Locke, David, Kennewick, Richard, Kennewick, Michael R. Jr., Freeman, Tom, Kennewick, Michael R. Sr., Elston, Stephen F.
• Granted Patent: US 7,693,720 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G10L 15/18 using natural language modelling

Abstract

Mobile systems and methods that overcomes the deficiencies of prior art speech-based interfaces for telematics applications through the use of a complete speech-based information query, retrieval, presentation and local or remote command environment. This environment makes significant use of context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users making queries or commands in multiple domains. Through this integrated approach, a complete speech-based natural language query and response environment can be created. The invention creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context and presenting the expected results for a particular question or command. The invention may organize domain specific behavior and information into agents, that are distributable or updateable over a wide area network. The invention can be used in dynamic environments such as those of mobile vehicles to control and communicate with both vehicle systems and remote systems and devices.

Claims

2. The mobile system according to claim 1, wherein the natural language speech processing system further comprises an event manager, said event manager coordinating interaction between components of the natural language speech processing system.

21-1. The-mobile system according to claim 1, wherein the speech unit is located remotely from the natural language speech processing system and the transceiver.

28. A method responsive to a user generated natural language speech utterance, comprising:

receiving the user generated natural language speech utterance, the user generated natural language speech utterance having at least one of a query and a command;

converting the user generated natural language speech utterance into an electronic signal;

retrieving said at least one of said query and said command from the electronic signal;

selecting a domain agent associated with said at least one of said query and said command;

forwarding said at least one of said query and said command to said domain agent, wherein said domain agent is an autonomous executable that receives, processes and responds to said at least one of saodquery and said command; and

transmitting a message associated with said at least one of said query and said command to a remotely located service.

29. The method according to claim 28, further comprising coding the electronic signal.

30. The method according to claim 28, further comprising

selecting a second domain agent, the second domain agent associated with at least one of a navigation system, a vehicle monitoring system, a security system, a vehicle control system and a vehicle media system;

and

forwarding a second message to said second domain agent.

31. The method according to claim 28, wherein said domain agent includes data associated with at least one of driving directions, travel information, restaurant information, vehicle systems information, safety information and entertainment information.

32. The method according to claim 28, wherein said domain agent includes information for communicating with the remotely located service.

33. The method according to claim 32, wherein the transmitting operation includes sending at least one of a query and a command to the remotely located service.

34. The method according to claim 28, wherein the device system is a remotely located device.

35. The method according to claim 28, wherein the transmitting operation with the remotely located service is via a network.

36. The method according to claim 28, wherein the remotely located service is one of a payment service provider, a customer relationship management system, a specialized service, a location service and a emergency service.

37. The method according to 28, wherein the transmitting operation with the remotely located service is via a wide-area RF transceiver.

38. The method according to 28, further comprising filtering-out background noise of the received user utterance.

39. The method according to 38, wherein the filtering-out operation is by at least using a filter employing adaptive echo cancellation.

40. The method according to claim 29, wherein the user generated natural language speech utterance is coded using an adaptive lossy audio compression.

41. The method according to claim 28, wherein the receiving operation of the user generated natural language speech utterance is remotely performed from the other operations.

42. The method according to claim 41, wherein the receiving operation of the user generated natural language speech utterance is performed in a vehicle.

43. The method according to claim 28, further comprising retrieving data from a network shared source, the network shared source is at least one of an agent, a user profile and a events history.

44. The mobile system according to claim 43, wherein the device system is at least one of a navigation system, a vehicle monitoring system, a security system, a vehicle control system and a vehicle media system.

45. The mobile system according to claim 43, wherein the at least one domain agent includes data associated with at least one of driving directions, travel information, restaurant information, vehicle systems information, safety information and entertainment information.

46. The mobile system according to claim 43, wherein the device system is a remotely located device.

47. The mobile system according to claim 43, wherein the device system is a remotely located service.

48. The mobile system according to claim 47, wherein the transmitting means communicates with the remotely located service via a network.

49. The mobile system according to claim 47, wherein the remotely located service is one of a payment service provider, a customer relationship management system, a specialized service, a location service and a emergency service.

50. The mobile system according to 43, wherein the transmitting means is a wide-area RF transceiver.

51. The mobile system according to 43, further comprising a filtering means that filters the received user generated natural language speech utterance.

52. The mobile system according to claim 43, further comprising a coder means that codes the user generated natural language speech utterance.

53. The mobile system according to claim 43, wherein the receiving means is remotely located from other mobile system components.

54. The mobile system according to claim 53, wherein the receiving means is located at a vehicle.

55. The mobile system according to claim 43, further comprising data retrieving means that retrieves data from a network shared source, the source is at least one of an agent, data, a user profile and a events history.

43-2. A mobile system responsive to a user generated natural language speech utterance, comprising:

receiving means that receives the user generated natural language speech utterance, the user generated natural language speech utterance having at least one of a query and a command;

converting means that converts the user generated natural language speech utterance into an electronic signal;

retrieving means that retrieves said at least one of said query and said command domain agent selecting means that selects a domain agent associated with said at least one of said query and said command;

forwarding means that forwards said at least one of said query and said command to said selected domain agent; and

transmitting means that transmits a message from said selected domain agent to a device system.