Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

Example-Based Grapheme-to-Phoneme Conversion for Thai

Paisarn Charoenpornsawat, Tanja Schultz

Carnegie Mellon University, USA

Several characteristics of the Thai writing system make Thai graphemeto- phoneme (G2P) conversion very challenging. In this paper, we propose an Example-Based Grapheme-to-Phoneme conversion approach. It generates the pronunciation of a word by selecting, modifying and combining pronunciations from syllables from training corpus. The best system achieves 80.99% word accuracy and 94.19% phone accuracy which significantly outperform previous approaches for Thai.

Full Paper

Bibliographic reference.  Charoenpornsawat, Paisarn / Schultz, Tanja (2006): "Example-based grapheme-to-phoneme conversion for Thai", In INTERSPEECH-2006, paper 1782-Tue3A3O.6.