Incorporating a Bayesian wide phonetic context model for acoustic rescoring

This paper presents a method for improving acoustic model precision by incorporating wide phonetic context units in speech recognition. The wide phonetic context model is constructed from several narrower context-dependent models based on the Bayesian framework. Such a composition is performed in order to avoid the crucial problem of a limited availability of training data and to reduce the model complexity. To enhance the model reliability due to unseen contexts and limited training data, flooring and deleted interpolation techniques are used. Experimental results show that this method gives improvement of the word accuracy with respect to the standard triphone model.