Improved DVQ algorithm for speech recognition: a new adaptive learning rule with neurons annihilation
Chakib Tadj, Franck Poirier · 1993
In this paper, three techniques are introduced to improve the DVQ algorithm. The first one consists in an automatic algorithm to determine the threshold oe, a function of the minimum class variance, by a cross validation procedure. The second improvement consists in a new adaptive learning rule based on a spatial geometry considerations. The algorithm is proposed to reduce an instability phenomenon which may appear during learning. Finally a criterion of neurons annihilation is proposed to remove unnecessary elements from the system to ensure network stability. Some experiments on real speech data are presented to show the effects of these three techniques on the network properties, including the learning time duration, the number of references and the recognition rate in each case. Key Words : Automatic Speech Recognition, Artificial Neural Network, Incremental Learning, Neurons Annihilation. TADJ Chakib, EuroSpeech, 1993 1. INTRODUCTION In recent years, there has been considerabl...