ISCA Archive Eurospeech 1993
ISCA Archive Eurospeech 1993

Bayesian regularisation methods in a hybrid MLP-HMM system

Steve Renals, David MacKay

We have applied Bayesian regularisation methods to multi-layer percepuon (MLP) training in the context of a hybrid MLP-HMM (hidden Markov model) continuous speech recognition system. The Bayesian framework adopted here allows an objective setting of the regularisation parameters, according to the training data. Experiments have been carried out on the ARPA Resource Management database,

Keywords: Speech Recognition, HMM, Neural Network, Regularisation, Bayesian