Connectionist Approaches to the Use of Markov Models for Speech Recognition

Hervé Bourlard, Nelson Morgan, Chuck Wooters
1990 Neural Information Processing Systems  
Previous work has shown the ability of Multilayer Perceptrons (MLPs) to estimate emission probabilities for Hidden Markov Models (HMMs). The advantages of a speech recognition system incorporating both MLPs and HMMs are the best discrimination and the ability to incorporate multiple sources of evidence (features, temporal context) without restrictive assumptions of distributions or statistical independence. This paper presents results on the speaker-dependent portion of DARPA's English language
more » ... Resource Management database. Results support the previously reported utility of MLP probability estimation for continuous speech recognition. An additional approach we are pursuing is to use MLPs as nonlinear predictors for autoregressive HMMs. While this is shown to be more compatible with the HMM formalism, it still suffers from several limitations. This approach is generalized to take account of time correlation between successive observations, without any restrictive assumptions about the driving noise.
dblp:conf/nips/BourlardMW90 fatcat:pmqntuuiancmna4pjedkufdosu