摘要 |
PURPOSE: A number voice recognition apparatus and a method thereof are provided to improve the performance of voice recognition without increasing complexity of voice model construction. CONSTITUTION: A number voice recognition apparatus extracts a feature vector from an input voice signal(220). The apparatus generates one or more number syllable candidates from a predetermined sound model based on syllable by using the extracted feature vector(230). The apparatus outputs a recognized number(240). [Reference numerals] (210) Voice signal is inputted; (220) Number voice recognition apparatus extracts a feature vector from an input voice signal; (230) Apparatus generates one or more number syllable candidates from a predetermined sound model based on syllable by using the extracted feature vector; (240) Apparatus outputs a recognized number; (AA) Start; (BB) End
|