VOICE RECOGNITION DEVICE

• US 20150279363A1
• Filed: 11/05/2012
• Published: 10/01/2015
• Est. Priority Date: 11/05/2012
• Status: Active Grant

• Current Assignee: Mitsubishi Electric Corporation
• Original Assignee: Mitsubishi Electric Corporation
• Inventors: Furumoto, Yuki
• Granted Patent: US 9,378,737 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• 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 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Because a voice recognition device in accordance with the present invention is configured in such a way as to be able to accept an operation of commanding a voice recognition start also when recognizing an uttered voice at all times, the voice recognition device can recognize an uttered voice by using a voice recognition method having a high recognition rate according to an operation of commanding a voice recognition start when a speaking person desires while avoiding the inconvenience of usually needing to perform a specific operation every time when making the voice recognition device perform recognition. As a result, the convenience is improved.

Claims

1. A voice recognition device that recognizes an uttered voice, said voice recognition device comprising:

a voice acquirer that detects and acquires said uttered voice;

a first voice recognizer that recognizes voice data acquired by said voice acquirer at all times even if the voice recognition device does not receive a voice recognition start command provided by a speaking person;

a voice recognition start commander that outputs a command signal for starting voice recognition;

a second voice recognizer that, when receiving the signal outputted by said voice recognition start commander, recognizes the voice data acquired by said voice acquirer; and

a controller that acquires and outputs a recognition result provided by said first voice recognizer or said second voice recognizer, wherein

said controller acquires the recognition result provided by said first voice recognizer, and, when not receiving the signal outputted by said voice recognition start commander, outputs the recognition result provided by said first voice recognizer to a device to which said voice recognition device is applied, whereas when receiving the signal outputted by said voice recognition start commander, acquires the recognition result provided by said second voice recognizer, and outputs the recognition result provided by said second voice recognizer while giving a higher priority to the recognition result provided by said second voice recognizer than to the recognition result provided by said first voice recognizer.

2. The voice recognition device according to claim 1, wherein said voice recognition device further includes a surrounding state acquirer that acquires a surrounding state, and said controller determines whether or not to output the recognition result provided by said first voice recognizer on a basis of the surrounding state acquired by said surrounding state acquirer.

3. The voice recognition device according to claim 2, wherein said surrounding state is information about a type of a screen displayed on a display of a device to which said voice recognition device is applied, and wherein said controller does not output the recognition result provided by said first voice recognizer when determining, on a basis of the information about the type of said screen, that said screen is a one to which a type causing adoption of the recognition result provided by said second voice recognizer is assigned.

4. The voice recognition device according to claim 2, wherein said surrounding state is information about a type of a function which is performed by a device to which said voice recognition device is applied, and wherein said controller does not output the recognition result provided by said first voice recognizer when determining, on a basis of the information about the type of said function, that said function is a one to which a type causing adoption of the recognition result provided by said second voice recognizer is assigned.

5. The voice recognition device according to claim 2, wherein said voice recognition device is mounted in a moving object and said surrounding state is a travelling state of said moving object, and wherein said controller does not output the recognition result provided by said first voice recognizer when determining, on a basis of the travelling state of said moving object, that said moving object is accelerating or moving at a high speed.

6. The voice recognition device according to claim 2, wherein said surrounding state is a sound volume of noise occurring in surroundings of said voice recognition device, and wherein said controller does not output the recognition result provided by said first voice recognizer when said noise sound volume is equal to or larger than a predetermined value.

7. The voice recognition device according to claim 2, wherein said controller displays whether or not said controller is in a state in which said controller does not output the recognition result provided by said first voice recognizer on a display of a device to which said voice recognition device is applied.

8. The voice recognition device according to claim 6, wherein said controller visually displays the noise sound volume acquired by said surrounding state acquirer on a display of a device to which said voice recognition device is applied.