COMMUNICATION SYSTEM AND METHOD BETWEEN AN ON-VEHICLE VOICE RECOGNITION SYSTEM AND AN OFF-VEHICLE VOICE RECOGNITION SYSTEM

• US 20170169825A1
• Filed: 02/28/2017
• Published: 06/15/2017
• Est. Priority Date: 06/24/2010
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: HUANG, Ritchie, VAGHEFINAZARI, Pedram, YAMAMOTO, Stuart
• Granted Patent: US 10,269,348 B2
• Time in Patent Office: Days
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• 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 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G10L 21/06 Transformation of speech into a non-audible representation, e.g. speech visualisation or speech processing for tactile aids G10L15/26 takes precedence
• CPC Class Codes: G10L 25/72 for transmitting results of analysis

Abstract

A vehicle based system and method for receiving voice inputs and determining whether to perform a voice recognition analysis using in-vehicle resources or resources external to the vehicle.

Claims

1-18. -18. (canceled)

19. A computer-implemented method in a vehicle, comprising:

obtaining a user voice input via at least one input device of the vehicle for at least generating a voice recognition result;

determining one or more characteristics of the user voice input;

determining a correlation between the voice recognition result and information associated with one or more off-board devices or systems of the vehicle at least in part by detecting that the voice recognition result corresponds to information unavailable within the vehicle; and

determining whether to process the user voice input using an in-vehicle voice recognition system or a system external to the vehicle based at leash upon the one or more characteristics of the user voice input and the correlation.

20. The method of claim 19, wherein detecting that the voice recognition result corresponds to information unavailable within the vehicle comprises detecting that the voice recognition result corresponds to at least one of:

obtaining news or other dynamic data, sending an email or text message, purchasing tickets to an event, making reservations, searching for a point of interest, or obtaining weather information or real-time traffic information.

21. The method of claim 19, wherein each of the one or more characteristics has a first selected threshold value, and wherein determining the one or more characteristics of the user voice input comprises determining at least one of:

a voice type, frequency, speed, prosody, intelligibility, tone, pitch, size, direction, volume, or duration of the user voice input.

22. The method of claim 21, wherein determining the correlation between the voice recognition result and information associated with the one or more off-board devices or systems of the vehicle is based on detecting that at least one characteristic of the user voice input does not exceed the first selected threshold value associated with the at least one characteristic.

23. The method of claim 19, further comprising:

using the in-vehicle voice recognition system to perform a computer based voice recognition process in the vehicle to the user voice input for generating the voice recognition result; and

determining a confidence value for the voice recognition result to indicate a likelihood that the voice recognition result is correct.

24. The method of claim 23, wherein determining the correlation between the voice recognition result and information associated with the one or more off-board devices or systems of the vehicle is based on detecting that the confidence value exceeds a second selected threshold value.

25. The method of claim 23, further comprising:

storing voice profiles of one or more users of the vehicle for enabling the in-vehicle voice recognition system to perform the computer based voice recognition process in the vehicle to one or more obtained user voice inputs.

26. The method of claim 19, wherein determining whether to process the user voice input using the in-vehicle voice recognition system or the system external to the vehicle is further based at least in part on determining whether there are connectivity issues between the in-vehicle voice recognition system and a server.

27. A system in a vehicle, comprising:

at least one processor configured to;

obtain a user voice input via at least one input device of the vehicle for at least generating a voice recognition result;

determine one or more characteristics of the user voice input;

determine a correlation between the voice recognition result and information associated with one or more off-board devices or systems of the vehicle at least in part by detecting that the voice recognition result corresponds to information unavailable within the vehicle; and

determine whether to process the user voice input using an in-vehicle voice recognition system or a system external to the vehicle based at least upon the one or more characteristics of the user voice input and the correlation.

28. The system of claim 27, wherein the at least one processor detects that the voice recognition result corresponds to information unavailable within the vehicle at least in part by detecting that the voice recognition result corresponds to at least one of:

obtaining news or other dynamic data, sending an email or text message, purchasing tickets to an event, making reservations, searching for a point of interest, or obtaining weather information or real-time traffic information.

29. The system of claim 27, wherein each of the one or more characteristics having a first selected threshold value, and the at least one processor is configured to determine the one or more characteristics of the user voice input by determining at least one of:

a voice type, frequency, speed, prosody, intelligibility, tone, pitch, size, direction, volume, or duration of the user voice input.

30. The system of claim 29, wherein the at least one processor is configured to determine the correlation between the voice recognition result and information associated with the one or more off-board devices or systems of the vehicle is based on detecting that at least one characteristic of the user voice input does not exceed the first selected threshold value associated with the at least one characteristic.

31. The system of claim 27, wherein the at least one processor is further configured to:

use the in-vehicle voice recognition system to perform a computer based voice recognition process in the vehicle to the user voice input for generating the voice recognition result; and

determine a confidence value for the voice recognition result to indicate a likelihood that the voice recognition result is correct.

32. The system of claim 31, wherein the at least one processor is configured to determine the correlation between the voice recognition result and information associated with the one or more off-board devices or systems of the vehicle is based on detecting that the confidence value exceeds a second selected threshold value.

34. The system of claim 27, wherein the at least one processor determines whether to process the user voice input using the in-vehicle voice recognition system or the system external to the vehicle further based at least in part on determining whether there are connectivity issues between the in-vehicle voice recognition system and a server.

35. A non-transitory computer-readable storage medium having computer-executable instructions, the instructions when executed cause at least one processor to:

obtain a user voice input via at least one input device of a vehicle for at least generating a voice recognition result;

determine one or more characteristics of the user voice input;

determine a correlation between the voice recognition result and information associated with one or more off-board devices or systems of the vehicle at least in part by detecting that the voice recognition result corresponds to information unavailable within the vehicle; and

determine whether to process the user voice input using an in-vehicle voice recognition system or a system external to the vehicle based at least upon the one or more characteristics of the user voice input and the correlation.

36. The non-transitory computer-readable storage medium of claim 35, wherein the instructions when executed cause the at least one processor to detect that the voice recognition result corresponds to information unavailable within the vehicle by detecting that the voice recognition result corresponds to at least one of:

obtaining news or other dynamic data, sending an email or text message, purchasing tickets to an event, making reservations, searching for a point of interest, or obtaining weather information or real-time traffic information.

37. The non-transitory computer-readable storage medium of claim 35, wherein each of the one or more characteristics has a first selected threshold value, and wherein determining the one or more characteristics of the user voice input comprises determining at least one of:

a voice type, frequency, speed, prosody, intelligibility, tone, pitch, size, direction, volume, or duration of the user voice input.

38. The non-transitory computer-readable storage medium of claim 37, wherein the instructions when executed cause the at least one processor to determine the correlation between the voice recognition result and information associated with the one or more off-board devices or systems of the vehicle based on detecting that at least one characteristic of the user voice input does not exceed the first selected threshold value associated with the at least one characteristic.