Grapheme-to-phoneme conversion is an important step in speech segmentation and synthesis. Many approaches are proposed in the literature to perform appropriate transcriptions: CART, FST, HMM, etc. In this paper we propose the use of an automatic algorithm that uses the transformation-based error-driven learning to match the phonetic transcription with the speakerís dialect and style. Different transcriptions based on word, part-of-speech tags, weak forms and phonotactic rules are validated. The experimental results show an improvement in the transcription using an objective measure. The articulation MOS score is also improved, as most of the changes in phonetic transcription affect coarticulation effects.
Bibliographic reference. Agüero, Pablo Daniel / Bonafonte, Antonio / Tulli, Juan Carlos (2009): "Improving consistence of phonetic transcription for text-to-speech", In INTERSPEECH-2009, 536-539.