Interspeech'2005 - Eurospeech
We propose a method for determining the canonical phonemic transcription of a word from its orthography using hidden Markov models. In the model, phonemes are the hidden states and graphemes the observations. Apart from one pre-processing step, the model is fully automatic. The paper describes the basic HMM framework and enhancements which use pre-processing, context dependent models and a syllable level stress model. In all cases the power of the framework lies in that training of the models (which includes alignment of graphemes and phonemes, training of transitions and training observation probabilities) is performed in a single step.
Bibliographic reference. Taylor, Paul (2005): "Hidden Markov models for grapheme to phoneme conversion", In INTERSPEECH-2005, 1973-1976.