Discriminative state-weighting of HMM-based speech recognizers

Abstract

Assuming that the score of a speech utterance is a weighted sum of hidden Markov model (HMM) log state-likelihoods, we propose a new method of finding discriminative state-weights recursively using the generalized probabilistic descent method. Experimental results showed that the recognizers with phoneme-based and word-based state-weights achieved 20% and 50% decrease in word error rate, respectively, for isolated word recognition, and 5% decrease for continuous speech recognition. Our approach yields recognition accuracies comparable to those of the previous approaches for continuous speech recognition, but it is much simpler to implement than others.