| 摘要 |
PROBLEM TO BE SOLVED: To reduce a misrecognition rate and raise operability of a voice recognition device by appropriately selecting two or more voice recognition dictionaries according to a skill level of a user. SOLUTION: The voice recognition device 10 performs voice recognition of an input voice by referring to the voice recognition dictionaries 11-1 to 11-4 and outputs a voice recognition result. The voice recognition device is provided with two or more voice recognition dictionaries according to predetermined classification, and the voice recognition device includes: a user's skill level determination means 16 which determines a user's skill level according to correcting operation to the voice recognition result and obtains a skill level determination result; a dictionary selection means 14 which selects voice recognition dictionaries to be used as selected voice recognition dictionaries from the voice recognition dictionaries based on the skill level determination result; and a voice recognition means 13 which performs voice recognition of the input voice by referring to the selected voice recognition dictionaries and obtains a voice recognition result. COPYRIGHT: (C)2007,JPO&INPIT
|
