Roles for Confidence Measures in Automatic Speech RecognitionInvestigator: Gethin Williams Supervisor: Steve Renals
It has been shown  that Artificial Neural Networks (ANNs), when trained as classifiers
in the appropriate manner, can accurately estimate Bayesian posterior probabilities. Bayesian
classifiers have many desirable qualities .
Despite these desirable qualities, ANNs have difficulty accomodating temporal variation present in the speech signal. One technique which allows the use of ANNs to classify speech sounds is to combine them with Hidden Markov Models (HMMs), forming an ANN/HMM hybrid . Such hybrids can be trained according to a Maximum A Posteriori (MAP) criterion, so as to produce optimal classifiers operating above the phone level.