Continuous speech recognition using a hierarchical Bayesian model

Abstract

Proposes a stochastic model for continuous speech recognition that provides automatic segmentation of spoken utterances into phonemes and facilitates the quantitative assessment of uncertainty associated with the identified utterance features. The model is specified hierarchically within the Bayesian paradigm. At the lowest level of the hierarchy, a Gibbs distribution is used to specify a probability distribution on all the possible partitions of the utterance. The number of partitioning elements which are phonemes is not specified a priori. At a higher level in the hierarchical specification, random variables representing phoneme durations and acoustic vector values axe associated with each phoneme and frame. Estimation of the posterior distribution is done using a Gibbs sampler scheme.