Automobile interface

• US 20070005206A1
• Filed: 07/01/2005
• Published: 01/04/2007
• Est. Priority Date: 07/01/2005
• Status: Active Grant

• Current Assignee: Bose Corporation
• Original Assignee: Bose Corporation
• Inventors: Lee, Steven, Hidden, William, Zhang, You, Hotary, James, Iyengar, Vasu, Faneuff, Jeffery
• Granted Patent: US 7,826,945 B2
• Time in Patent Office: Days
• US Class Current: 701/36
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G08G 1/09675 where a selection from the received information takes place in the vehicle
• CPC Class Codes: G08G 1/096775 where the origin of the information is a central station
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 1/2757 by data transmission, e.g. downloading
• CPC Class Codes: H04M 1/6091 including a wireless interface

Abstract

An automotive system provides an integrated user interface for control and communication functions in an automobile or other type of vehicle. The user interface supports voice enabled interactions, as well as other modes of interaction, such as manual interactions using controls such as dashboard or steering wheel mounted controls. The system also includes interfaces to devices in the vehicle, such as wireless interfaces to mobile devices that are brought into the vehicle. The system also provides interfaces to information sources such as a remote server, for example, for accessing information.

Claims

1. A method for providing a voice enabled user interface comprising:

storing general configuration information for the interface;

storing user-specific configuration information for the interface;

enabling processing of a speech input from a user using the general configuration information and the user-specific configuration information; and

selectively updating the user-specific configuration information based on a result of processing the speech input.

2. The method of claim 1 wherein the updating is performed on correct recognition of the input when a score associated with the input indicates that an incorrect recognition hypothesis has a score within a predetermined threshold.

3. The method of claim 2 wherein the updating is performed without requiring further speech input from the user.

4. The method of claim 1 wherein the user-specific configuration information includes user-specific pronunciation information for lexical items for which general pronunciation information is included in the general configuration information.

5. The method of claim 1 wherein updating the user-specific configuration information is performed during use of the interface.

6. The method of claim 5 wherein the updating is based on mis-recognition of the speech input from the user.

7. The method of claim 5 wherein updating the user-specific configuration information is based on results of recognition of a speech input from the user.

8. A method for providing a voice enabled user interface comprising:

configuring the interface to process an utterance of an identifier in conjunction with redundant or disambiguating information associated with the identifier.

9. The method of claim 8 further comprising retrieving the additional or disambiguating information from a database associating the identifier with said information.

10. The method of claim 9 wherein the database comprises a contact database.

11. The method of claim 8 wherein the redundant or ambiguous information is directly concatenated with the identifier.

12. The method of claim 8 wherein the identifier comprises a name, and the redundant or disambiguating information comprises initials of the name.

13. A method for providing a voice enabled user interface comprising:

providing configuration information for each of a plurality of users of the interface;

determining a user of the interface; and

adapting the interface using the configuration information for the determined user.

14. The method of claim 13 wherein determining the user includes applying a speaker identification process to a spoken input from the user.

15. A method of associating a first device and a second device over a communication medium comprising:

generating data at the first device;

presenting the data generated at the first device to a user;

transmitting an associating request to the second device;

accepting, on the second device, the data as input from the user permitting the association of the first and the second devices.

16. The method of claim 15 wherein the first device comprises a vehicle-based device and the second device comprises a mobile device.

17. The method of claim 16 wherein the mobile device comprises one of a mobile telephone and a PDA.

18. The method of claim 15 further includes a step of initiating by pressing a button on the first device.

19. The method of claim 15 further comprising associating the first device and the second device according to a Bluetooth communication approach.

20. A method for configuring a voice enabled user interface comprising:

at a first device, receiving contact data from a second device;

at the first device, requesting additional data from a data source to augment the contact data; and

configuring the user interface using the received contact data from the second device and the additional data from the data source.

21. The method of claim 20 wherein the first device comprises a vehicle-based device and the second device comprises a mobile device.

22. The method of claim 20 wherein the data source resides at a remote server.

23. The method of claim 20 wherein the additional data requested from the remote server includes information related to an entry in the contact data.

24. The method of claim 23 wherein the entry in the contact data includes a name and associated telephone number, and the requested additional data includes address information associated with the entry.

25. A method for providing an in-vehicle voice enabled user interface comprising:

accepting a communication command from a user; and

determining destination information from the communication command and commanding a navigation system based on the determined destination information.

26. The method of claim 25 wherein the communication command comprises a telephone dialing command.

27. The method of claim 25 further comprising determining a route to the destination determined from the communication command.

28. The method of claim 25 wherein the communication command comprises a spoken command.

29. The method of claim 25 wherein the step of determining is based on an association between the communication command and the destination information in a contact database.

30. A method for providing an in-vehicle voice enabled user interface comprising:

obtaining text street information from a navigation system;

converting the text street information into its spoken equivalent; and

presenting the spoken equivalent to the user.

31. A method for providing an in-vehicle voice enabled interface comprising:

presenting a visual cue to a user on a graphic display, wherein the visual cue is suitable for detection by the user in the user'"'"'s peripheral vision without requiring the user to look directly at the display.

32. The method of claim 31 wherein the visual cue is related to a state of the spoken interface.

33. The method of claim 32 wherein presenting the visual cue includes providing an indication that the spoken interface is in a state to accept a spoken command

34. The method of claim 32 wherein presenting the visual cue includes providing an indication that the spoken interface has accepted a spoken command from the user.

35. A method for providing an in-vehicle voice enabled interface comprising:

adjusting one or more control settings related to an acoustic environment at an onset of a spoken interaction, including recording the control settings prior to adjustment; and

restoring the control settings after the spoken interaction.

36. The method of claim 35 wherein the control settings include a volume setting.

37. The method of claim 36 wherein the volume setting includes a speech volume setting.

38. The method of claim 35 wherein the control settings include a setting for a noise-generating device.

39. The method of claim 38 wherein the setting for the noise-generating device includes a fan setting.

40. A method for providing a multi-modal in-vehicle user interface comprising:

accepting a first part of a command in a first interaction mode;

detecting a condition associated with the user interface;

determining a second interaction mode based on the detected condition; and

accepting a second part of the command in the second interaction mode;

wherein the first interaction mode and the second interaction mode are each one of a spoken interaction mode and a manual interaction mode.

41. The method of claim 40 further comprising presenting to the user information substantially related to only a single one of the first interaction mode and the second interaction mode.

42. The method of claim 40 wherein detecting the condition associated with the user interface includes detecting a noise level in the environment of the user interface.

43. The method of claim 40 wherein accepting the first part of the command and accepting the second part of the command are performed to provide a continuous entry of the command without requiring repetition of the first part of the command.

44. A method for providing a voice enabled user interface comprising:

accepting text specifications of vocabulary items;

determining pronunciations for the vocabulary items;

accepting a spoken input from a user;

automatically recognizing vocabulary items in the spoken input using the determined pronunciations; and

if a score associated with the recognized vocabulary items falls in a predetermined range, determining a pronunciation of one or more of the vocabulary items from the accepted spoken input.

45. A method for establishing an association between devices comprising:

initiating an associating procedure at a first device;

detecting one or more candidate devices at the first device;

accepting a selection of a second device of the candidate devices from a user;

providing associating information to the user from the first device;

transmitting a request from the first device to the second device; and

accepting the associating information from the user at the second device.

46. A system comprising:

a storage for general configuration information for the interface and user-specific configuration information for the interface; and

a speech processor configured to accept a speech input from a user and use the general configuration information and the user-specific configuration information, and configured to selectively update the user-specific configuration information based on a result of processing the speech input.

47. Software stored on a machine readable medium comprising instructions for causing a processor to:

store general configuration information for the interface;

store user-specific configuration information for the interface;

process a speech input from a user using the general configuration information and the user-specific configuration information; and

selectively update the user-specific configuration information based on a result of processing the speech input.

48. A system adapted to associate a first device and a second device over a communication medium comprising:

means for generating data at the first device;

means for presenting the data generated at the first device to a user;

means for transmitting an associating request to the second device;

means for accepting, on the second device, the data as input from the user permitting the association of the first and the second devices.

49. A system for configuring a voice enabled user interface comprising:

a first device including means for receiving contact data from a second device and means requesting additional data from a data source to augment the contact data;

wherein the first device further includes means for configuring the user interface using the received contact data from the second device and the additional data from the data source.

50. Software stored on a machine readable medium comprising instructions for causing a processor to:

receive contact data from a second device;

request additional data from a data source to augment the contact data; and

configure a user interface using the received contact data from the second device and the additional data from the data source.

51. An in-vehicle voice enabled user interface comprising:

means for accepting a communication command from a user; and

means for determining destination information from the communication command and commanding a navigation system based on the determined destination information.

52. Software stored on a machine-readable medium comprising instructions for causing a processor to:

accept a communication command from a user; and

determine destination information from the communication command and commanding a navigation system based on the determined destination information.

53. An in-vehicle voice enabled interface comprising:

means for presenting a visual cue to a user on a graphic display, wherein the visual cue is suitable for detection by the user in the user'"'"'s peripheral vision without requiring the user to look directly at the display.