| 摘要 |
PROBLEM TO BE SOLVED: To provide a voice recognition method for recommending use of misrecognized synonymous words to a user as replaced words of recognition object words when recognition vocabularies are misrecognized, even if the recognition vocabularies to be used are wholly registered from first, and to provide a voice recognition device. SOLUTION: A prescribed input voice, pronounced by the user from a voice input part 101, is acquired to recognize the input voice with a voice recognition part 106 so as to be presented to the user by outputting a recognition from GUI 102 or a voice output part 110. Determination as to whether the recognition result is correct is received from the user, and when the recognition result is misrecognized, correct recognition object words for the input voice are designated. The synonymous words of the correctly recognized object words are retrieved, and recommended to the user to be used as the replaced words of the correctly recognized object words. In addition, an operation command, corresponding to the correct recognition object words, is further made to correspond with the synonym words. COPYRIGHT: (C)2005,JPO&NCIPI
|
