VOICE RECOGNITION DEVICE AND NAVIGATION DEVICE

• US 20130253933A1
• Filed: 04/08/2011
• Published: 09/26/2013
• Est. Priority Date: 04/08/2011
• Status: Active Grant

• Current Assignee: Mitsubishi Electric Corporation
• Original Assignee: Mitsubishi Electric Corporation
• Inventors: Maruta, Yuzo
• Granted Patent: US 9,230,538 B2
• Time in Patent Office: Days
• US Class Current: 704/246
• CPC Class Codes: B60R 16/0373 Voice control in general G10L
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 2025/786 Adaptive threshold

Abstract

A voice recognition device 100 includes: a vehicle state detecting unit 7 for detecting a vehicle state of a vehicle having the voice recognition device mounted thereon; an acoustic data matching unit 5 for matching an acoustic feature value converted by a sound analyzing unit 3 with a recognition dictionary stored in a recognition dictionary storage unit 4 to recognize a voice input to a microphone 1; a recognition parameter setting unit 10 for setting a recognition parameter at the time when the voice input to the microphone 1 is recognized; and a control unit 9 for instructing the recognition parameter setting unit 10 to change the recognition parameter when the vehicle state detected by the vehicle state detecting unit 7 satisfies a predetermined condition.

Claims

1-17. -17. (canceled)

18. A voice recognition device comprising:

a sound collecting unit for acquiring an input voice;

a voice processing unit for processing the voice acquired by the sound collecting unit into a digital signal;

a sound analyzing unit for sound-analyzing the voice signal processed by the voice processing unit to convert an acoustic feature into an acoustic feature value indicated in time series;

a recognition dictionary describing a correspondence between the acoustic feature value converted by the sound analyzing unit and recognition vocabulary; and

an acoustic matching unit for matching the acoustic feature value with the recognition dictionary to recognize the voice that is input to the sound collecting unit,

the device further comprising;

a vehicle state detecting unit for detecting a vehicle state of a vehicle having the voice recognition device mounted thereon;

an audio output detecting unit for detecting a volume of a voice signal that is output from an audio device installed within the vehicle;

a gain setting unit for setting a voice acquisition gain of the sound collecting unit;

a recognition parameter setting unit for setting a recognition parameter at the time when the acoustic matching unit recognizes the voice input to the sound collecting unit; and

a control unit for instructing the recognition parameter setting unit to change the recognition parameter when the vehicle state detected by the vehicle state detecting unit and the volume of the voice signal detected by the audio output detecting unit satisfies a predetermined condition.

20. The voice recognition device according to claim 18, wherein the control unit returns the recognition parameter to a steady value when the vehicle state of the vehicle or the volume of the voice signal output from the audio device match with the predetermined condition.

22. The voice recognition device according to claim 20, wherein the control unit returns the recognition parameter to a steady value, when the change in the vehicle speed is less than the threshold and the change in the vehicle speed continues to be less than the threshold during a period going back for a predetermined time from a point of time when the operation input is received, or returns the voice acquisition gain to a steady value when the volume of the voice signal is less than the threshold and the volume of the voice signal continues to be less than the threshold during a period going back for a predetermined time from the point of time when the operation input is received.

23. The voice recognition device according to claim 18, wherein:

the vehicle state detecting unit detects a vehicle speed of the vehicle; and

upon receiving an operation input to instruct a start of voice recognition processing, the control unit instructs the recognition parameter setting unit to change the recognition parameter when a change in the vehicle speed detected by the vehicle state detecting unit during a period going back for a predetermined time from a point of time when the corresponding operation input is received is not less than a threshold.

24. The voice recognition device according to claim 18, wherein when the change in the vehicle speed is not less than the threshold, the control unit sets a time-out time for detecting the end of a voice input among the recognition parameters to a value greater than a steady value.

25. The voice recognition device according to claim 18, wherein the control unit instructs the gain setting unit to set the voice acquisition gain to a value smaller than a steady value when the volume of the voice signal detected by the audio output detecting unit is not less than a threshold.

26. The voice recognition device according to claim 18, wherein upon receiving an operation input to instruct a start of voice recognition processing, the control unit determines whether or not the volume of the voice signal immediately before the reception of the operation input is not less than the threshold.

19. A voice recognition device comprising:

a sound collecting unit for acquiring an input voice;

a voice processing unit for processing the voice acquired by the sound collecting unit into a digital signal;

a sound analyzing unit for sound-analyzing the voice signal processed by the voice processing unit to convert an acoustic feature into an acoustic feature value indicated in time series;

a recognition dictionary describing a correspondence between the acoustic feature value converted by the sound analyzing unit and recognition vocabulary; and

an acoustic matching unit for matching the acoustic feature value with the recognition dictionary to recognize the voice that is input to the sound collecting unit,

the device further comprising;

a vehicle state detecting unit for detecting a vehicle state of a vehicle having the voice recognition device mounted thereon;

an audio output detecting unit for detecting a volume of a voice signal that is output from an audio device installed within the vehicle;

a gain setting unit for setting a voice acquisition gain of the sound collecting unit;

a recognition parameter setting unit for setting a recognition parameter at the time when the acoustic matching unit recognizes the voice input to the sound collecting unit;

a voice recognition stop processing unit for stopping the voice recognition processing of at least one of the voice processing unit, the sound analyzing unit, and the acoustic matching unit when the stop of the voice recognition processing is instructed; and

a control unit for instructing the recognition parameter setting unit to change the recognition parameter or instructing the voice recognition stop processing unit to stop the voice recognition processing when the vehicle state detected by the vehicle state detecting unit and the volume of the voice signal detected by the audio output detecting unit satisfy a predetermined condition.

21. The voice recognition device according to claim 19, wherein when the vehicle state does not satisfy the predetermined condition and does not satisfy continuously the predetermined condition during a period going back for a predetermined time from a point of time when an operation input of a start of the voice recognition processing is received, the control unit cancels the instruction to stop the voice recognition processing.

27. The voice recognition device according to claim 19, wherein the vehicle state detecting unit detects a turning angle or rotational speed of a steering wheel of the vehicle, and the control unit gives an instruction to stop the voice recognition processing when the steering wheel turning angle or rotational speed acquired by the vehicle state detecting unit is not less than the threshold.

28. The voice recognition device according to claim 19, wherein:

the vehicle state detecting unit acquires lighting information of winkers of the vehicle; and

the control unit gives an instruction to stop the voice recognition processing when the winkers are lit.

29. The voice recognition device according to claim 19, wherein:

the vehicle state detecting unit acquires traveling direction information of the vehicle; and

the control unit refers to the traveling direction information acquired by the vehicle state detecting unit, and gives an instruction to stop the voice recognition processing when a difference between a past traveling direction of the vehicle and a current traveling direction of the vehicle is not less than a threshold.

30. The voice recognition device according to claim 19, wherein:

the vehicle state detecting unit acquires traveling direction information of the vehicle and white line information on a road; and

the control unit refers to the traveling direction information and white line information acquired by the vehicle state detecting unit, and gives an instruction to stop the voice recognition processing when a difference between the traveling direction of the vehicle and an extending direction of the white line is not less than a threshold.

31. The voice recognition device according to claim 19, wherein the control unit refers to map information and current position information of the vehicle, and when the vehicle enters an intersection, the control unit gives an instruction to stop the voice recognition processing.

32. The voice recognition device according to claim 19, wherein when an instruction to stop the voice recognition processing is given to the voice recognition stop processing unit, the control unit invalidates the acceptance of an operation input to instruct a start of the voice recognition.

33. The voice recognition device according to claim 19, wherein the control unit returns the recognition parameter to a steady value when the vehicle state of the vehicle or the volume of the voice signal output from the audio device match with the predetermined condition.

34. The voice recognition device according to claim 19, wherein:

the vehicle state detecting unit detects a vehicle speed of the vehicle; and

upon receiving an operation input to instruct a start of voice recognition processing, the control unit instructs the recognition parameter setting unit to change the recognition parameter when a change in the vehicle speed detected by the vehicle state detecting unit during a period going back for a predetermined time from a point of time when the corresponding operation input is received is not less than a threshold.

35. The voice recognition device according to claim 19, wherein when the change in the vehicle speed is not less than the threshold, the control unit sets a time-out time for detecting the end of a voice input among the recognition parameters to a value greater than a steady value.

36. The voice recognition device according to claim 19, wherein the control unit instructs the gain setting unit to set the voice acquisition gain to a value smaller than a steady value when the volume of the voice signal detected by the audio output detecting unit is not less than a threshold.

37. The voice recognition device according to claim 19, wherein upon receiving an operation input to instruct a start of voice recognition processing, the control unit determines whether or not the volume of the voice signal immediately before the reception of the operation input is not less than the threshold.