VOICE RECOGNITION DEVICE AND PROGRAM

摘要

PROBLEM TO BE SOLVED: To inform a user of whether which part of an inputted voice is inarticulately spoken according to the result of voice recognition. SOLUTION: A voice recognition device has its voice analysis part 11 configured to extract a metrical feature parameter and a phonetic feature parameter by taking a voice analysis. A voice recognition part 12 performs voice recognition by using the phonetic feature parameter. A voice synthesis part 13 performs voice synthesis based upon the result of the voice recognition by the voice recognition part 12 and the metrical feature parameter. COPYRIGHT: (C)2004,JPO&NCIPI