TY  - JOUR
T1  - A Matlab Implementation of a Speech Recognition System Using HMM Models
AU - , A. Cherif AU - , F. Chabane AU - , M. Talbi AU - , F.L. Agha 
JO  - Journal of Engineering and Applied Sciences
VL  - 2
IS  - 11
SP  - 1587
EP  - 1591
PY  - 2007
DA  - 2001/08/19
SN  - 1816-949x
DO  - jeasci.2007.1587.1591
UR  - https://makhillpublications.co/view-article.php?doi=jeasci.2007.1587.1591
KW  - Speech recognition system
KW  -HMM
KW  -mono-speaker
KW  -Matlab environment
KW  -code back conception
AB  - In this study, we present a speech recognition interface designed for vocal control. The implementation has been realized under the Matlab environment with scripts in C. The program uses the statistical HMM (Hidden Markov Models) for speech modeling, the K-means, Baum-welch algorithms for training  and  codebook  conception  and  finally the Viterbi decoding algorithm for the recognition process. The recognized word decision is based on the maximal likehood value. The speech database is constituted of 1000 words mono-speaker associated with a denoising module before be applied to the developed interface.
ER  -