Hybrid NN/HMM-Based Speech Recognition with a Discriminant Neural Feature Extraction

Abstract

In this paper, we present a novel hybrid architecture for continuous speech recognition systems. It consists of a continuous HMM system extended by an arbitrary neural network that is used as a preprocessor that takes several frames of the feature vector as input to produce more discrimin(cid:173) ative feature vectors with respect to the underlying HMM system. This hybrid system is an extension of a state-of-the-art continuous HMM sys(cid:173) tem, and in fact, it is the first hybrid system that really is capable of outper(cid:173) forming these standard systems with respect to the recognition accuracy. Experimental results show an relative error reduction of about 10% that we achieved on a remarkably good recognition system based on continu(cid:173) ous HMMs for the Resource Management 1 OOO-word continuous speech recognition task.