Cohen, M., Franco, H., Morgan, N., Rumelhart, D., & Abrash, V. (1992, June). Multiple-state context-dependent phonetic modeling with MLP. In Proceedings of Speech Research Symposium XII.
Abstract
Earlier hybrid multilayer perceptron (MLP)/hidden Markov model (HMM) continuous speech recognition systems have not modeled context-dependent phonetic effects, sequences of distributions for phonetic models, or gender-based speech consistencies. In this paper we present a new MLP architecture and training procedure for modeling context-dependent phonetic classes with a sequence of distributions. A new training procedure that “smooths” networks with different degrees of context-dependence is proposed in order to obtain a robust estimate of the context-dependent probabilities. We have used this new architecture to model generalized biphone
phonetic contexts. Tests with the speaker-independent DARPA Resource Management database have shown average reductions in word error rates of 20% in both the word-pair grammar and no-grammar cases, compare with our earlier context-independent MLP/HMM hybrid.