INTERSPEECH 2004 - ICSLP
We report on ongoing work on a pronunciation model based on explicit representation of the evolution of multiple linguistic feature streams. In this type of model, most pronunciation variation is viewed as the result of asynchrony between features and changes in feature values. We have implemented such a model using dynamic Bayesian networks. In this paper, we extend our previous work with a mechanism for learning feature asynchrony probabilities from data. We present experimental results on a word classification task using phonetic transcriptions of utterances from the Switchboard corpus.
Bibliographic reference. Livescu, Karen / Glass, James (2004): "Feature-based pronunciation modeling with trainable asynchrony probabilities", In INTERSPEECH-2004, 677-680.