CDHMM parameters selection for speaker-independent phone recognition in continuous speech system
Zaineb Ben Messaoud, Ahmed Ben Hamida · 2010
Pattern recognition has long been a topic of fundamental importance in a wide range of science and technology. Over the years there have been a range of several tasks developed for speech recognition. While in recent years speech recognizer evaluation has focused on LVCSR research, we believe that evaluating recognition at the phone level is important since the words are always represented by the concatenation of phones units. These phones are acoustically modeled by the predominant static model in automatic speech recognition remains the Hidden Markov Model `HMM'. In this paper, we investigate the behavior of speaker-independent phone recognition in continuous speech based on the technique of HMM. This study focus on the selection of an optimal model topology in order to achieve a robust phone recognition system which accomplishes the tradeoff between model size and data training. To evaluate and compare the performance of our conceived system to other previous works, we choose the standard TIMIT Database and the platform HTK. We obtain a phone recognition correct rate 69.33 percent and accuracy rate of 63.05 percent which are comparable with others works.