s Multiple-State Context-Dependent Phonetic Modeling with MLP
Michael M. Cohen, Horacio Franco, Nelson H. Morgan, David E. Rumelhart, Victor Abrash · 1992
arlier hybrid multilayer perceptron (MLP)/hidden Markov model (HMM) continuous speech recognition sysr g tems have not modeled context-dependent phonetic effects, sequences of distributions for phonetic models, o ender-based speech consistencies. In this paper we present a new MLP architecture and training procedure for t " modeling context-dependent phonetic classes with a sequence of distributions. A new training procedure tha smooths" networks with different degrees of context-dependence is proposed in order to obtain a robust estip mate of the context-dependent probabilities. We have used this new architecture to model generalized biphone honetic contexts. Tests with the speaker-independent DARPA Resource Management database have shown d w average reductions in word error rates of 20% in both the word-pair grammar and no-grammar cases, compare ith our earlier context-independent MLP/HMM hybrid. P 1. Introduction revious work by Morgan, Bourlard, et al. [1, 2] has shown both the...