| 摘要 |
A system and a method for recognizing a voice by using class-based histogram equalization are provided to bring plural classes to a voice characteristic parameter and perform the histogram equalization by class, thereby preventing the performance of the voice recognition system from being deteriorated by effectively reducing sound discordance existing in a sound characteristic parameter. A system for recognizing a voice comprises a characteristic extractor(101), a characteristic corrector(102), and a voice recognizer(103). The characteristic extractor divides a digital voice signal into a frame unit with regular time intervals and extracts a sound characteristic parameter. The characteristic corrector generates characteristic correction components by class by multiplying each class weight after applying histogram equalization to the characteristic parameter, and obtains a characteristic parameter where sound discordance is corrected by adding the entire characteristic correction components by class to the characteristic correction components by class. The voice recognizer performs voice recognition from the corrected characteristic parameter. |
