Tied posteriors: an approach for effective introduction of context dependency in hybrid NN/HMM LVCSR

Abstract

This paper presents a method to improve the recognition rate of hybrid connectionist/HMM speech recognition systems. At the same time this approach allows the easy introduction of context dependent models in the hybrid framework. The approach is based on a standard hybrid connectionist/HMM recognizer, in which the neural nets are trained to estimate the a posteriori probabilities for all phones in each input frame. In the approach presented here, the probabilities of the neural nets are used to replace the codebook of a tied-mixture HMM system. Therefore the resulting system is called tied posterior. The advantages of this structure are that an arbitrary HMM-topology can be used, and that all context dependency and all clustering techniques used in tied-mixture systems can be applied to this hybrid speech recognition system. The approach has been evaluated on the Wall Street Journal (WSJ) database, with the result, that it outperforms the standard hybrid approach on this task.