User mobility in a voice recognition environment

• US 7,099,825 B1
• Filed: 03/15/2002
• Issued: 08/29/2006
• Est. Priority Date: 03/15/2002
• Status: Active Grant

• Current Assignee: T-Mobile Innovations LLC (Deutsche Telekom AG)
• Original Assignee: Sprint Communications Company LP (Deutsche Telekom AG)
• Inventors: Cook, Fred S.
• Primary Examiner(s): Chawan, Vijay B.
• Application Number:
  US10/099,729
• Time in Patent Office: 1,628 Days
• Field of Search: 704/231, 704/270, 704/275, 704/251, 704/246, 379/88.02, 379/202.01, 379/88.13, 455/563
• US Class Current: 704/251
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A voice recognition system is disclosed. A device receives a signal indicating a user ID and transfers a signal indicating its device ID and the user ID to a processing system. The processing system obtains a device profile based on the device ID and obtains a user profile based on the user ID. The processing system generates voice recognition data customized for the device and the user based on the device profile and the user profile. The processing system transfers a signal indicating the voice recognition data to the device. The device indicates voice command readiness in response to the voice recognition data. The device receives a voice command from the user and translates the voice command based on the customized voice recognition data.

Claims

1. A method of operating a voice recognition system, the method comprising:

receiving a first signal indicating a first user ID for a first user into a first device;

transferring a second signal indicating a first device ID for the first device and indicating the first user ID to a processing system;

in the processing system, obtaining a first device voice recognition profile based on the first device ID and obtaining a first user voice recognition profile based on the first user ID;

in the processing system, generating a first set of voice recognition data customized for the first device and the first user based on the first device voice recognition profile and the first user voice recognition profile;

transferring a third signal indicating the first set of the voice recognition data from the processing system to the first device;

in the first device, indicating voice command readiness in response to the first set of the voice recognition data;

receiving a first voice command from the first user into the first device; and

in the first device, translating the first voice command based on the first set of the voice recognition data.

2. The method of claim 1 further comprising:

receiving a fourth signal indicating the first user ID into a second device;

transferring a fifth signal indicating a second device ID for the second device and indicating the first user ID to the processing system;

in the processing system, obtaining a second device voice recognition profile based on the second device ID and obtaining the first user voice recognition profile based on the first user ID, wherein the second device voice recognition profile is different from the first device voice recognition profile to reflect different voice recognition capabilities between the first device and the second device;

in the processing system, generating a second set of the voice recognition data customized for the second device and the first user based on the second device voice recognition profile and the first user voice recognition profile;

transferring a sixth signal indicating the second set of the voice recognition data from the processing system to the second device;

in the second device, indicating voice command readiness in response to the second set of the voice recognition data;

receiving a second voice command from the first user into the second device; and

in the second device, translating the second voice command based on the second set of the voice recognition data.

3. The method of claim 1 further comprising:

receiving a fourth signal indicating a second user ID for a second user into the first device;

transferring a fifth signal indicating the first device ID and indicating the second user ID to a processing system;

in the processing system, obtaining the first device voice recognition profile based on the first device ID and obtaining a second user voice recognition profile based on the second user ID, wherein the second user voice recognition profile is different from the first user voice recognition profile to reflect different voice recognition characteristics between the first user and the second user;

in the processing system, generating a second set of the voice recognition data customized for the first device and the second user based on the first device voice recognition profile and the second user voice recognition profile;

transferring a sixth signal indicating the second set of the voice recognition data from the processing system to the first device;

in the first device, indicating voice command readiness in response to the second set of the voice recognition data;

receiving a second voice command from the second user into the first device; and

in the first device, translating the second voice command based on the second set of the voice recognition data.

4. The method of claim 1 further comprising

receiving a fourth signal indicating a second user ID for a second user into a second device;

transferring a fifth signal indicating a second device ID for the second device and indicating the second user ID to the processing system;

in the processing system, obtaining a second device voice recognition profile based on the second device ID and obtaining a second user voice recognition profile based on the second user ID, wherein the second device voice recognition profile is different from the first device voice recognition profile to reflect different voice recognition capabilities between the first device and the second device, and wherein the second user voice recognition profile is different from the first user voice recognition profile to reflect different voice recognition characteristics between the first user and the second user;

in the processing system, generating a second set of the voice recognition data customized for the second device and the second user based on the second device voice recognition profile and the second user voice recognition profile;

transferring a sixth signal indicating the second set of the voice recognition data from the processing system to the second device;

in the second device, indicating voice command readiness in response to the second set of the voice recognition data;

receiving a second voice command from the second user into the second device; and

in the second device, translating the second voice command based on the second set of the voice recognition data.

5. The method of claim 1 further comprising:

transferring a fourth signal indicating new voice recognition data for the first user from the first device to the processing system; and

in the processing system, modifying the first user voice recognition profile based on the new voice recognition data for the first user.

6. The method of claim 1 further comprising:

transferring a fourth signal indicating new voice recognition data for the first device from the first device to the processing system; and

in the processing system, modifying the first device voice recognition profile based on the new voice recognition data for the first device.

7. The method of claim 1 wherein the second signal further indicates the first user voice recognition profile.

8. The method of claim 1 wherein the second signal further indicates the first device voice recognition profile.

9. The method of claim 1 wherein generating the first set of the voice recognition data customized for the first device and the first user based on the first device voice recognition profile and the first user voice recognition profile comprises translating a command recognition library for the first user into a format suitable for the first device.

10. The method of claim 1 wherein translating the first voice command based on the first set of the voice recognition data comprises converting audible user speech into an electronic signal indicating the first voice command.

11. A voice recognition system comprising:

a first device configured to receive a first signal indicating a first user ID for a first user, transfer a second signal indicating a first device ID for the first device and indicating the first user ID, receive a third signal indicating a first set of voice recognition data, indicate voice command readiness in response to the first set of the voice recognition data, receive a first voice command from the first user, and translate the first voice command based on the first set of the voice recognition data; and

a processing system configured to receive the second signal, obtain a first device voice recognition profile based on the first device ID, obtain a first user voice recognition profile based on the first user ID, generate the first set of the voice recognition data customized for the first device and the first user based on the first device voice recognition profile and the first user voice recognition profile, and transfer the third signal.

12. The voice recognition system of claim 11 further comprising:

a second device configured to receive a fourth signal indicating the first user ID, transfer a fifth signal indicating a second device ID for the second device and indicating the first user ID, receive a sixth signal indicating a second set of the voice recognition data, indicate voice command readiness in response to the second set of the voice recognition data, receive a second voice command from the first user, and translate the second voice command based on the second set of the voice recognition data; and

wherein

the processing system is further configured to receive the fifth signal, obtain a second device voice recognition profile based on the second device ID wherein the second device voice recognition profile is different from the first device voice recognition profile to reflect different voice recognition capabilities between the first device and the second device, obtain the first user voice recognition profile based on the first user ID, generate the second set of the voice recognition data customized for the second device and the first user based on the second device voice recognition profile and the first user voice recognition profile, and transfer the sixth signal.

13. The voice recognition system of claim 11 wherein:

the first device is further configured to receive a fourth signal indicating a second user ID for a second user, transfer a fifth signal indicating the first device ID and indicating the second user ID, receive a sixth signal indicating a second set of the voice recognition data, indicate voice command readiness in response to the second set of the voice recognition data, receive a second voice command from the second user, and translate the second voice command based on the second set of the voice recognition data; and

the processing system is further configured to receive the fifth signal, obtain the first device voice recognition profile based on the first device ID, obtain a second user voice recognition profile based on the second user ID wherein the second user voice recognition profile is different from the first user voice recognition profile to reflect different voice recognition characteristics between the first user and the second user, generate the second set of the voice recognition data customized for the first device and the second user based on the first device voice recognition profile and the second user voice recognition profile, and transfer the sixth signal.

14. The voice recognition system of claim 11 further comprising:

a second device configured to receive a fourth signal indicating a second user ID for a second user, transfer a fifth signal indicating a second device ID for the second device and indicating the second user ID, receive a sixth signal indicating a second set of the voice recognition data, indicate voice command readiness in response to the second set of the voice recognition data, receive a second voice command from the second user, and translate the second voice command based on the second set of the voice recognition data; and

wherein

the processing system is further configured to receive the fifth signal, obtain a second device voice recognition profile based on the second device ID wherein the second device voice recognition profile is different from the first device voice recognition profile to reflect different voice recognition capabilities between the first device and the second device, obtain a second user voice recognition profile based on the second user ID wherein the second user voice recognition profile is different from the first user voice recognition profile to reflect different voice recognition characteristics between the first user and the second user, generate the second set of the voice recognition data customized for the second device and the second user based on the second device voice recognition profile and the second user voice recognition profile, and transfer the sixth signal.

15. The voice recognition system of claim 11 wherein:

the first device is further configured to transfer a fourth signal indicating new voice recognition data for the first user; and

the processing system is further configured to modify the first user voice recognition profile based on the new voice recognition data for the first user.

16. The voice recognition system of claim 11 wherein:

the first device is further configured to transfer a fourth signal indicating new voice recognition data for the first device; and

the processing system is further configured to modify the first device voice recognition profile based on the new voice recognition data for the first device.

17. The voice recognition system of claim 11 wherein the second signal further indicates the first user voice recognition profile.

18. The voice recognition system of claim 11 wherein the second signal further indicates the first device voice recognition profile.

19. The voice recognition system of claim 11 wherein the processing system is configured to translate a command recognition library for the first user into a format suitable for the first device.

20. The voice recognition system of claim 11 wherein the first device is configured to convert audible user speech into an electronic signal indicating the first voice command based on the first set of the voice recognition data.

21. A method of operating a processing system for a voice recognition system, the method comprising:

receiving a first signal from a first device indicating a first user ID for a first user and a first device ID for the first device;

obtaining a first device voice recognition profile based on the first device ID and obtaining a first user voice recognition profile based on the first user ID;

generating a first set of voice recognition data customized for the first device and the first user based on the first device voice recognition profile and the first user voice recognition profile; and

transferring a second signal to the first device indicating the first set of the voice recognition data.

22. The method of claim 21 further comprising:

receiving a third signal from a second device indicating the first user ID and a second device ID for the second device;

obtaining a second device voice recognition profile based on the second device ID wherein the second device voice recognition profile is different from the first device voice recognition profile to reflect different voice recognition capabilities between the first device and the second device and obtaining the first user voice recognition profile based on the first user ID;

generating a second set of the voice recognition data customized for the second device and the first user based on the second device voice recognition profile and the first user voice recognition profile; and

transferring a fourth signal to the second device indicating the second set of the voice recognition data.

23. The method of claim 21 further comprising

receiving a third signal from the first device indicating a second user ID for a second user and the first device ID;

obtaining the first device voice recognition profile based on the first device ID and obtaining a second user voice recognition profile based on the second user ID wherein the second user voice recognition profile is different from the first user voice recognition profile to reflect different voice recognition characteristics between the first user and the second user;

generating a second set of the voice recognition data customized for the first device and the second user based on the first device voice recognition profile and the second user voice recognition profile; and

transferring a fourth signal to the first device indicating the second set of the voice recognition data.

24. The method of claim 21 further comprising

receiving a third signal from a second device indicating a second user ID for a second user and a second device ID for the second device;

obtaining a second device voice recognition profile based on the second device ID and obtaining a second user voice recognition profile based on the second user ID, wherein the second device voice recognition profile is different from the first device voice recognition profile to reflect different voice recognition capabilities between the first device and the second device, and wherein the second user voice recognition profile is different from the first user voice recognition profile to reflect different voice recognition characteristics between the first user and the second user;

generating a second set of the voice recognition data customized for the second device and the second user based on the second device voice recognition profile and the second user voice recognition profile; and

transferring a fourth signal to the second device indicating the second set of the voice recognition data.

25. The method of claim 21 further comprising:

receiving a third signal indicating new voice recognition data for the first user from the first device; and

modifying the first user voice recognition profile based on the new voice recognition data for the first user.

26. The method of claim 21 further comprising:

receiving a fourth signal indicating new voice recognition data for the first device from the first device; and

modifying the first device voice recognition profile based on the new voice recognition data for the first device.

27. The method of claim 21 wherein the first signal further indicates the first user voice recognition profile.

28. The method of claim 21 wherein the first signal further indicates the first device voice recognition profile.

29. The method of claim 21 wherein generating the first set of the voice recognition data customized for the first device and the first user based on the first device voice recognition profile and the first user voice recognition profile comprises translating a command recognition library for the first user into a format suitable for the first device.

30. The method of claim 21 wherein the first set of the voice recognition data is configured to allow the first device to convert audible user speech into an electronic signal indicating a voice command.

31. A processing system for a voice recognition system, the processing system comprising:

a communication interface configured to receive a first signal from a first device indicating a first user ID for a first user and a first device ID for the first device and transfer a second signal to the first device indicating a first set of voice recognition data; and

a control system coupled to the communication interface and configured to obtain a first device voice recognition profile based on the first device ID, obtain a first user voice recognition profile based on the first user ID, and generate the first set of the voice recognition data customized for the first device and the first user based on the first device voice recognition profile and the first user voice recognition profile.

32. The processing system of claim 31 wherein:

the communication interface is further configured to receive a third signal from a second device indicating the first user ID and a second device ID for the second device and transfer a fourth signal to the second device indicating a second set of the voice recognition data; and

the control system is further configured to obtain a second device voice recognition profile based on the second device ID wherein the second device voice recognition profile is different from the first device voice recognition profile to reflect different voice recognition capabilities between the first device and the second device, obtain the first user voice recognition profile based on the first user ID, and generate the second set of the voice recognition data customized for the second device and the first user based on the second device voice recognition profile and the first user voice recognition profile.

33. The processing system of claim 31 wherein:

the communication interface is further configured to receive a third signal from the first device indicating a second user ID for a second user and the first device ID and transfer a fourth signal to the first device indicating a second set of the voice recognition data; and

the control system is further configured to obtain the first device voice recognition profile based on the first device ID, obtain a second user voice recognition profile based on the second user ID wherein the second user voice recognition profile is different from the first user voice recognition profile to reflect different voice recognition characteristics between the first user and the second user, and generate the second set of the voice recognition data customized for the first device and the second user based on the first device voice recognition profile and the second user voice recognition profile.

34. The processing system of claim 31 wherein:

the communication interface is further configured to receive a third signal from a second device indicating a second user ID for a second user and a second device ID for the second device and transfer a fourth signal to the second device indicating a second set of the voice recognition data; and

the control system is further configured to obtain a second device voice recognition profile based on the second device ID wherein the second device voice recognition profile is different from the first device voice recognition profile to reflect different voice recognition capabilities between the first device and the second device, obtain a second user voice recognition profile based on the second user ID wherein the second user voice recognition profile is different from the first user voice recognition profile to reflect different voice recognition characteristics between the first user and the second user, and generate the second set of the voice recognition data customized for the second device and the second user based on the second device voice recognition profile and the second user voice recognition profile.

35. The processing system of claim 31 wherein:

the communication interface is further configured to receive a third signal from the first device indicating new voice recognition data for the first user; and

the control system is further configured to modify the first user voice recognition profile based on the new voice recognition data for the first user.

36. The processing system of claim 31 wherein:

the communication interface is further configured to receive a third signal from the first device indicating new voice recognition data for the first device; and

the control system is further configured to modify the first device voice recognition profile based on the new voice recognition data for the first device.

37. The processing system of claim 31 wherein the first signal further indicates the first user voice recognition profile.

38. The processing system of claim 31 wherein the first signal further indicates the first device voice recognition profile.

39. The processing system of claim 31 wherein the control system is configured to translate a command recognition library for the first user into a format suitable for the first device.

40. The processing system of clam 31 wherein the first set of the voice recognition data is configured to allow the first device to convert audible user speech into an electronic signal indicating a voice command.

41. A software product for a voice recognition system, the software product comprising:

software configured to direct a control system to receive a first user ID for a first user and a first device ID for a first device from a communication interface, obtain a first device voice recognition profile based on the first device ID, obtain a first user voice recognition profile based on the first user ID, generate a first set of voice recognition data customized for the first device and the first user based on the first device voice recognition profile and the first user voice recognition profile, and transfer the first set of the voice recognition data to the communication interface for transfer to the first device; and

a storage medium operational to store the software.

42. The software product of claim 41 wherein the software is further configured to direct the control system to receive the first user ID and a second device ID for a second device from the communication interface, obtain a second device voice recognition profile based on the second device ID wherein the second device voice recognition profile is different from the first device voice recognition profile to reflect different voice recognition capabilities between the first device and the second device, obtain a first user voice recognition profile based on the first user ID, generate a second set of the voice recognition data customized for the second device and the first user based on the second device voice recognition profile and the first user voice recognition profile, and transfer the second set of the voice recognition data to the communication interface for transfer to the second device.

43. The software product of claim 41 wherein the software is further configured to direct the control system to receive a second user ID for a second user and the first device ID from the communication interface, obtain the first device voice recognition profile based on the first device ID, obtain a second user voice recognition profile based on the second user ID wherein the second user voice recognition profile is different from the first user voice recognition profile to reflect different voice recognition characteristics between the first user and the second user, generate a second set of the voice recognition data customized for the first device and the second user based on the first device voice recognition profile and the second user voice recognition profile, and transfer the second set of the voice recognition data to the communication interface for transfer to the first device.

44. The software product of claim 41 wherein the software is further configured to direct the control system to receive a second user ID for a second user and a second device ID for a second device from the communication interface, obtain a second device voice recognition profile based on the second device ID wherein the second device voice recognition profile is different from the first device voice recognition profile to reflect different voice recognition capabilities between the first device and the second device, obtain a second user voice recognition profile based on the second user ID wherein the second user voice recognition profile is different from the first user voice recognition profile to reflect different voice recognition characteristics between the first user and the second user, generate a second set of the voice recognition data customized for the second device and the second user based on the second device voice recognition profile and the second user voice recognition profile, and transfer the second set of the voice recognition data to the communication interface for transfer to the second device.

45. The software product of claim 41 wherein the software is further configured to direct the control system to receive new voice recognition data for the first user from the communication interface and modify the first user voice recognition profile based on the new voice recognition data for the first user.

46. The software product of claim 41 wherein the software is further configured to direct the control system to receive new voice recognition data for the first device from the communication interface and modify the first device voice recognition profile based on the new voice recognition data for the first device.

47. The software product of claim 41 wherein the software is further configured to direct the control system to receive the first user voice recognition profile from the communication interface.

48. The software product of claim 41 wherein the software is further configured to direct the control system to receive the first device voice recognition profile from the communication interface.

49. The software product of claim 41 wherein the software is configured to direct the control system to translate a command recognition library for the first user into a format suitable for the first device.

50. The software product of claim 41 wherein the first set of the voice recognition data is configured to allow the first device to convert audible user speech into an electronic signal indicating a voice command.