Pronunciation lexicons can range from fully graphemic (modeling each word using the orthography directly) to fully phonemic (first mapping each word to a phoneme string). Between these two options lies a continuum of modeling options. We analyze techniques that can improve the accuracy of a graphemic system without requiring significant effort to design or implement. The analysis is performed in the context of the IARPA Babel project, which aims to develop spoken term detection systems for previously unseen languages rapidly, and with minimal human effort. We consider techniques related to letter-to-sound mapping and language-independent syllabification of primarily graphemic systems, and discuss results obtained for six languages: Cebuano, Kazakh, Kurmanji Kurdish, Lithuanian, Telugu and Tok Pisin.
Cite as: Davel, M., Barnard, E., Heerden, C.v., Hartmann, W., Karakos, D., Schwartz, R., Tsakalidis, S. (2015) Exploring minimal pronunciation modeling for low resource languages. Proc. Interspeech 2015, 538-542, doi: 10.21437/Interspeech.2015-199
@inproceedings{davel15_interspeech,
author={Marelie Davel and Etienne Barnard and Charl van Heerden and William Hartmann and Damianos Karakos and Richard Schwartz and Stavros Tsakalidis},
title={{Exploring minimal pronunciation modeling for low resource languages}},
year=2015,
booktitle={Proc. Interspeech 2015},
pages={538--542},
doi={10.21437/Interspeech.2015-199}
}