Improved phone recognition using Bayesian triphone models

A crucial issue in triphone based continuous speech recognition is the large number of models to be estimated against the limited availability of training data. This problem can be relieved by composing a triphone model from less context-dependent models. This paper introduces a new statistical framework, derived from the Bayesian principle, to perform such a composition. The potential power of this new framework is explored, both algorithmically and experimentally, by an implementation with hidden Markov modeling techniques. This implementation is applied to the recognition of the 39-phone set on the TIMIT database. The new model achieves 74.4% and 75.6% accuracy, respectively, on the core and complete test sets