摘要 |
PROBLEM TO BE SOLVED: To improve a recognition rate and accuracy of a person's utterance voice under all noise environments. SOLUTION: The voice recognition device performs recognition processing of the person's utterance voice collected by a non-contact type microphone which is used off the person's body and collects air-propagated sound of the person's utterance voice and converts it into an electric signal, and by a contact type microphone which is used in contact with the person's body and collects the body-transmitted sound of the person's utterance voice and converts it into an electric signal, respectively, and outputs a final voice recognition result based on the results using the non-contact type microphone and the contact type microphone. COPYRIGHT: (C)2007,JPO&INPIT
|