Discriminative Training of CDHMMs for Maximum Relative Separation Margin

Abstract

In this paper, we propose a new discriminative training method for estimating CDHMM (continuous density hidden Markov model) in speech recognition, based on the principle of maximizing the minimum relative multi-class separation margin. We show that the new training criterion can be formulated as a standard constrained minimax optimization problem. Then we show that the optimization problem can be solved by a GPD (generalized probabilistic descent) algorithm. Experimental results on E-set and Alphabet tasks (ISOLET database) showed that the new training criterion can achieve significant (up to 21%) error rate reduction over the popular MCE (minimum classification error) training method.