Hybrid neural network/hidden Markov model continuous-speech recognition
Michael Cohen, Horacio Franco, Nelson H. Morgan, David E. Rumelhart, Victor Abrash · 1992
n M In this paper we present a hybrid multilayer perceptron (MLP)/hidde arkov model (HMM) speaker-independent continuous-speech recognib tion system, in which the advantages of both approaches are combined y using MLPs to estimate the state-dependent observation probabilities p of an HMM. New MLP architectures and training procedures are resented which allow the modeling of multiple distributions for phonetic a p classes and context-dependent phonetic classes. Comparisons with ure HMM system illustrate advantages of the hybrid approach both in terms of recognition accuracy and number of parameters required. 1. INTRODUCTION - o Hidden Markov models (HMMs) are used in most current state f-the-art continuous-speech recognition systems. This approach is u limited by the need for strong statistical assumptions that are nlikely to be valid for speech. Techniques using multilayer peri ceptrons (MLPs) for probability estimation have recently been ntroduced [1] which reduce the assumption o...