TY  - JOUR
T1  - A Segment Based Approach of Hidden Markov Models for Speech Recognition
AU - , Rafik Djemili AU - , Mouldi Bedda AU - , Hocine Bourouba 
JO  - Asian Journal of Information Technology
VL  - 5
IS  - 11
SP  - 1172
EP  - 1176
PY  - 2006
DA  - 2001/08/19
SN  - 1682-3915
DO  - ajit.2006.1172.1176
UR  - https://makhillpublications.co/view-article.php?doi=ajit.2006.1172.1176
KW  - Speech recognition
KW  -hidden markov models
KW  -vector quantization
KW  -segment models
KW  -grouped vectors
AB  - In this study propose a new approach in using Hidden Markov Models (HMMs) for speech recognition. Although HMMs are the state-of-the art speech recognition systems, they suffer from some inherent limitations. One of these limitations is the independence assumption in the HMMs formalism. In the approach described in this study, we use in the vector quantization process, grouped vectors of different length to explicitly model the natural correlation between adjacent frames, instead of using a single vector in the standard method. The system is tested on an Arabic isolated digits (0-9) recognition task, our method achieves a 21% reduction in word error rate evaluation compared with the standard approach.
ER  -