Hierarchies of Neural Networks for Connectionist Speech Recognition

Abstract

We present a principled framework for context-dependent hierarchical connectionist HMM speech recognition. Based on a divide-and-conquer strategy, our approach uses an Agglomerative Clustering algorithm based on Information Divergence (ACID) to automatically design a soft classifier tree for an arbitrary large number of HMM states. Nodes in the classifier tree are instantiated with small estimators of local conditional posterior probabilities, in our case feed-forward neural networks. Our framework represents an effective decomposition of state posteriors with advantages over traditional acoustic models. We evaluate the effectiveness of our Hierarchies of Neural Networks (HNN) on the Switchboard large vocabulary conversational speech recognition (LVCSR) corpus.