Journal Search Engine
The Journal of The Korea Institute of Intelligent Transport Systems Vol.6 No.3 pp.87-94
에너지와 VQ를 이용한 음성 인식
Speech Recognition Using the Energy and VQ
Abstract
In this paper, the performance of the speech recognition and speaker adaptation methods are studied. The speech recognition using energy state and VQ(Vector Quantization) is suggested and the speaker adaptation methods(Maximum a posteriori probability estimation, linear specrum estimation) are considered. The experimental results show that recognition ration using energy state is 2-3 % better than that of general VQ.