We propose an approach to grapheme-to-phoneme conversion based on a probabilistic method: Conditional Random Fields (CRF). CRF give a long term prediction, and assume a relaxed state independence condition. Moreover, we propose an algorithm to the one-to-one letter to phoneme alignment needed for CRF training. This alignment is based on discrete HMMs. The proposed system is validated on two pronunciation dictionaries. Different CRF features are studied: POS-tag, context size, unigram versus bigram. Our approach compares favorably with the performance of the state-of-the-art Joint-Multigram Models for the quality of the pronunciations, but provides better recall and precision measures for multiple pronunciation variants generation.
Bibliographic reference. Illina, Irina / Fohr, Dominique / Jouvet, Denis (2011): "Grapheme-to-phoneme conversion using conditional random fields", In INTERSPEECH-2011, 2313-2316.