Hidden Markov models with context-sensitive observations for grapheme-to-phoneme conversion

Hidden Markov models (HMMs) have proven useful in various aspects of speech technology from automatic speech recognition through speech synthesis, speech segmentation and grapheme-to-phoneme conversion to part-of-speech tagging. Traditionally, context is modelled at the hidden states in the form of context-dependent models. This paper constitutes an extension to this approach; the underlying concept is to model context at the observations for HMMs with discrete observations and discrete probability distributions. The HMMs emit context-sensitive discrete observations and are evaluated with a grapheme-to-phoneme conversion system.