Communication system and method between an on-vehicle voice recognition system and an off-vehicle voice recognition system

• US 9,564,132 B2
• Filed: 09/25/2015
• Issued: 02/07/2017
• 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
• Primary Examiner(s): GUERRA-ERAZO, EDGAR X
• Application Number:
  US14/866,063
• Publication Number:
  US 20160012822A1
• Time in Patent Office: 501 Days
• Field of Search: 704/233, 704/235, 704/243, 704/246, 704/270, 704/270.1, 704/275, 704/277, 704/278
• US Class Current: 1/1
• 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. A computer based method in a vehicle, comprising:

receiving a representation of first voice input;

performing a computer based voice recognition in the vehicle to the first voice input representation for generating a first voice recognition result;

determining a confidence value of the in-vehicle performed voice recognition process representing a likelihood that the first voice recognition result is correct;

determining that the voice recognition process to the first voice input representation should be performed external to the vehicle if the confidence value is lower than a first threshold; and

transmitting the first voice input representation to an external system in response to the determination that the voice recognition process should be performed external to the vehicle.

2. The computer based method of claim 1, further comprising:

determining a first context of the first voice input representation; and

determining whether a voice recognition process should be performed to the first voice input representation by a computer based voice recognition system in the vehicle or using a voice recognition system that is external to the vehicle, based upon the first context.

3. The computer based method of claim 2, wherein determining the first context uses at least one of a type of vehicle key pressed by a first user in the vehicle and/or information displayed on an output device in the vehicle.

4. The computer based method of claim 3, wherein the information displayed on the output device is at least one of audio information, video information, and/or navigation information.

5. The computer based method of claim 1, further comprising:

determining if a wireless transmission connection between the vehicle and the external system exceeds a minimum threshold when the determination is to use the external voice recognition system; and

determining that the voice recognition process should be performed using the voice recognition system in the vehicle if the wireless transmission connection quality is lower than the minimum threshold.

6. The computer based method of claim 1, wherein the first voice input representation voice input representation is received from a first user of the vehicle, the method further comprising:

transmitting profile information about at least one of the first user and/or the vehicle to the external system.

7. The computer based method of claim 1, further comprising:

determining a first characteristic of the first voice input representation; and

determining whether a voice recognition process should be performed to the first voice input representation by a computer based voice recognition system in the vehicle or using a voice recognition system that is external to the vehicle based upon the first characteristic.

8. The computer based method of claim 7, wherein the first characteristic is at least one of a voice type, frequency, speed, prosody, intelligibility, tone, pitch, size, direction, volume and/or duration.

9. The computer based method of claim 7, further comprising:

determining if a wireless transmission connection between the vehicle and the external system exceeds a minimum threshold when the determination is to use the external voice recognition system; and

determining that the voice recognition process should be performed using the voice recognition system in the vehicle to the representation of the first voice input representation if the wireless transmission connection quality is lower than the minimum threshold.

10. The computer based method of claim 7, wherein the first voice input representation is received from a first user of the vehicle, the method further comprising:

transmitting profile information about at least one of the first user and/or the vehicle to the external system.

11. A system in a vehicle, comprising:

a microphone configured to receive a first voice input representation from a first user;

a voice recognition location unit configured to determine whether a voice recognition process should be performed by a voice recognition system in the vehicle or external to the vehicle, the voice recognition system performing a computer based voice recognition in the vehicle to the first voice input for generating a first voice recognition result;

a confidence value unit configured to determine a confidence value of the in-vehicle performed voice recognition process representing a likelihood that the first voice recognition result is correct; and

a communications unit configured to transmit the first voice input representation to an external system in response to a determination that the voice recognition process should be performed external to the vehicle;

wherein the determination is generated by the voice recognition location unit responsive to the confidence value being lower than a first threshold.

12. The system of claim 11, further comprising:

a context unit configured to determine a first context of the first voice input representation;

wherein the voice recognition location unit is configured to determine whether a voice recognition process should be performed to the first voice input representation by the voice recognition system in the vehicle or external to the vehicle based upon the first context.

13. The system of claim 11, wherein the communications unit is configured to determine if a wireless transmission connection between the vehicle and the external system exceeds a minimum threshold when the determination is to use the external voice recognition system;

and

wherein the voice recognition location unit is configured to determine that the voice recognition process to the first voice input representation should be performed using the voice recognition system in the vehicle if the wireless transmission connection quality is lower than the minimum threshold.

14. The system of claim 11, wherein the communication system is configured to transmit profile information about at least one of the first user and the vehicle to the external system.

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

receiving a first voice input representation from a first user of the vehicle;

performing computer based voice recognition to the first voice input representation in the vehicle for generating a first voice recognition result;

determining a confidence value of the in-vehicle performed voice recognition process representing a likelihood that the first voice recognition result is correct;

determining that the voice recognition process to the first voice input representation should be performed external to the vehicle if the confidence value is lower than a first threshold; and

transmitting the first voice input representation to an external system in response to the determination that the voice recognition process should be performed external to the vehicle.

16. The non-transitory computer-readable storage medium of claim 15, further comprising instructions for causing the computer to perform:

determining a first context of the first voice input representation; and

determining whether a voice recognition process should be performed to the first voice input representation by a computer based voice recognition system in the vehicle or external to the vehicle based upon the first context.

17. The non-transitory computer-readable storage medium of claim 15, further comprising instructions for causing the computer to perform:

determining if a wireless transmission connection between the vehicle and the external system exceeds a minimum threshold when the determination is to use the external voice recognition system; and

determining that the voice recognition process should be performed using the voice recognition system in the vehicle if the wireless transmission connection quality is lower than the minimum threshold.

18. The non-transitory computer-readable storage medium of claim 15, further comprising instructions for causing the computer to perform:

transmitting profile information about at least one of the first user and the vehicle to the external system.