Voice recognition device

摘要

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.

主权项

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.