Voice recognition device controller

• US 20070094033A1
• Filed: 10/10/2006
• Published: 04/26/2007
• Est. Priority Date: 10/20/2005
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Satomura, Masashi, Nagashima, Hisayuki
• Granted Patent: US 7,933,776 B2
• Time in Patent Office: Days
• US Class Current: 704/272
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology

Abstract

A voice recognition device controller is provided, which is capable of properly determining a user'"'"'s leaning level in speech so as to provide an efficient interaction. It includes a voice input unit 2 for receiving speech input from a user, a voice recognition unit 3 for recognizing the input speech, a response output unit 10 for outputting a response to the user, and a device control unit 11 for controlling a device based on a recognition result of the voice recognition unit 3. It further includes an input item count detection unit 4 for detecting the number of items identified from the recognized speech among a given number of items necessary to control the device, a reference input item count setting unit 6 for setting a reference value for the number of items identified from the speech, an input item count comparison unit 7 for comparing the number of items detected by the input item count detection unit 4 with the reference value set by the reference input item count setting unit 6, a skill level determination unit 8 for determining the user'"'"'s skill level in speech based on a comparison result, and a response control unit 9 for controlling the response output according to the determined skill level.

Claims

1. A voice recognition device controller having a voice input unit configured to receive speech input from a user, a voice recognition unit configured to recognize the speech input to the voice input unit, a response output unit configured to output a response to the user, and a device control unit configured to control a device based on a recognition result of the voice recognition unit, the voice recognition device controller comprising:

an input item count detection unit configured to detect the number of items identified from the speech recognized by the voice recognition unit among a given number of items necessary to control the device;

a reference input item count setting unit configured to set a reference value for the number of items identified from the speech based on the content of the input speech;

an input item count comparison unit configured to compare the number of items detected by the input item count detection unit with the reference value for the number of items set by the reference input item count setting unit;

a learning level determination unit configured to determine a learning level in speech of the user based on a comparison result of the input item count comparison unit; and

a response control unit configured to control the response output from the response output unit according to the learning level determined by the learning level determination unit.

2. A voice recognition device controller according to claim 1, further comprising a learning level storage unit configured to updatably store a user'"'"'s temporary learning level in speech,

wherein the reference input item count setting unit sets the reference value for the number of items identified from the speech based on the user'"'"'s temporary learning level in speech stored by the learning level storage unit.

3. A voice recognition device controller according to claim 2, wherein:

the device includes a plurality of types of device;

the learning level storage unit stores the user'"'"'s temporary learning level in speech for each type of device;

the reference input item count setting unit sets the reference value for the number of items identified from the speech for each type of device;

the input item count comparison unit compares the number of items detected by the input item count detection unit with the reference value for the number of items set for each type of device; and

the learning level determination unit determines the user'"'"'s learning level in speech for each type of device based on the comparison result of the input item count comparison unit.

4. A voice recognition device controller according to claim 3, wherein:

a plurality of the types of devices are each provided with a plurality of types of operational objects that can be operated by the user;

the given number of items necessary to control the device include items necessary to operate the operational objects;

the learning level storage unit stores the user'"'"'s temporary learning level in speech for each type of device and for each type of operational object;

the reference input item count setting unit sets the reference value for the number of items identified from the speech for each type of device and for each type of operational object;

the input item count comparison unit compares the number of items detected by the input item count detection unit with the reference value for the number of items set for each type of device and for each type of operational object; and

the learning level determination unit determines the user'"'"'s learning level in speech for each type of device and for each type of operational object based on the comparison result of the input item count comparison unit.

5. A voice recognition device controller according to claim 2, wherein the learning level storage unit updates the user'"'"'s temporary learning level in speech stored in the learning level storage unit, based on a determination result of the learning level determination unit.

6. A voice recognition device controller according to claim 3, wherein the learning level storage unit updates the user'"'"'s temporary learning level in speech stored in the learning level storage unit, based on the determination result of the learning level determination unit.

7. A voice recognition device controller according to claim 4, wherein the learning level storage unit updates the user'"'"'s temporary learning level in speech stored in the learning level storage unit, based on the determination result of the learning level determination unit.

8. A voice recognition device controller according to claim 1, wherein the response control unit includes a unit configured to control a response in such a way as to prompt the user for a given number of items, with the given number set according to the learning level determined by the learning level determination unit, among items not identified from the speech recognized by the voice recognition unit, if any, among the given number of items necessary to control the device.

9. A voice recognition device controller according to claim 2, wherein the response control unit includes a unit configured to control a response in such a way as to prompt the user for a given number of items, with the given number set according to the learning level determined by the learning level determination unit, among items not identified from the speech recognized by the voice recognition unit, if any, among the given number of items necessary to control the device.

10. A voice recognition device controller according to claim 1, mounted on a movable body and further comprising a driving load detection unit configured to detect a driving load on the user who is the driver of the movable body, wherein the reference input item count setting unit sets the reference value for the number of items identified from the speech based on the content of the input speech and the driving load detected by the driving load detection unit.

11. A voice recognition device controller according to claim 2, mounted on a movable body and further comprising a driving load detection unit configured to detect a driving load on the user who is the driver of the movable body, wherein the reference input item count setting unit sets the reference value for the number of items identified from the speech based on the user'"'"'s temporary learning level in speech stored by the learning level storage unit and the driving load detected by the driving load detection unit.

12. A voice recognition device controller according to claim 3, mounted on a movable body and further comprising a driving load detection unit configured to detect a driving load on the user who is the driver of the movable body, wherein the reference input item count setting unit sets the reference value for the number of items identified from the speech based on the user'"'"'s temporary learning level in speech stored by the learning level storage unit and the driving load detected by the driving load detection unit.

13. A voice recognition device controller according to claim 4, mounted on a movable body and further comprising a driving load detection unit configured to detect a driving load on the user who is the driver of the movable body, wherein the reference input item count setting unit sets the reference value for the number of items identified from the speech based on the user'"'"'s temporary learning level in speech stored by the learning level storage unit and the driving load detected by the driving load detection unit.

14. A voice recognition device controller according to claim 5, mounted on a movable body and further comprising a driving load detection unit configured to detect a driving load on the user who is the driver of the movable body, wherein the reference input item count setting unit sets the reference value for the number of items identified from the speech based on the user'"'"'s temporary learning level in speech stored by the learning level storage unit and the driving load detected by the driving load detection unit.

15. A voice recognition device controller according to claim 6, mounted on a movable body and further comprising a driving load detection unit configured to detect a driving load on the user who is the driver of the movable body, wherein the reference input item count setting unit sets the reference value for the number of items identified from the speech based on the user'"'"'s temporary learning level in speech stored by the learning level storage unit and the driving load detected by the driving load detection unit.

16. A voice recognition device controller according to claim 7, mounted on a movable body and further comprising a driving load detection unit configured to detect a driving load on the user who is the driver of the movable body, wherein the reference input item count setting unit sets the reference value for the number of items identified from the speech based on the user'"'"'s temporary learning level in speech stored by the learning level storage unit and the driving load detected by the driving load detection unit.

17. A voice recognition device controller according to claim 10, wherein the response control unit includes a unit configured to control a response in such a way as to prompt the user for a given number of items, with the given number set according to the learning level determined by the learning level determination unit and the driving load detected by the driving load detection unit, among items not identified from the speech recognized by the voice recognition unit, if any, among the given number of items necessary to control the device.

18. A voice recognition device controller according to claim 11, wherein the response control unit includes a unit configured to control a response in such a way as to prompt the user for a given number of items, with the given number set according to the learning level determined by the learning level determination unit and the driving load detected by the driving load detection unit, among items not identified from the speech recognized by the voice recognition unit, if any, among the given number of items necessary to control the device.

19. A method of controlling a voice recognition device having a voice input step configured to receive speech input from a user, a voice recognition step configured to recognize the speech input to the voice input step, a response output step configured to output a response to the user, and a device control step configured to control a device based on a recognition result of the voice recognition step, the method comprising the steps of:

an input item count detection step configured to detect the number of items identified from the speech recognized by the voice recognition step among a given number of items necessary to control the device;

a reference input item count setting step configured to set a reference value for the number of items identified from the speech based on the content of the input speech;

an input item count comparison step configured to compare the number of items detected by the input item count detection step with the reference value for the number of items set by the reference input item count setting step;

a learning level determination step configured to determine a learning level in speech of the user based on a comparison result of the input item count comparison step; and

a response control step configured to control the response output from the response output step according to the learning level determined by the learning level determination step.

20. A voice recognition device controller having a voice input means for receiving speech input from a user, a voice recognition means for recognizing the speech input to the voice input means, a response output means for outputting a response to the user, and a device control means for controlling a device based on a recognition result of the voice recognition means, the voice recognition device controller comprising:

an input item count detecting means for detecting the number of items identified from the speech recognized by the voice recognition means among a given number of items necessary to control the device;

a reference input item count setting means for setting a reference value for the number of items identified from the speech based on the content of the input speech;

an input item count comparing means for comparing the number of items detected by the input item count detection means with the reference value for the number of items set by the reference input item count setting means;

a learning level determination means for determining a learning level in speech of the user based on a comparison result of the input item count comparison means; and

a response control means for controlling the response output from the response output means according to the learning level determined by the learning level determination means.