ISCA Archive Interspeech 2006
ISCA Archive Interspeech 2006

Pronunciation variant-based multi-path HMMs for syllables

Annika Hämäläinen, Louis ten Bosch, Lou Boves

Recent research suggests that it is more appropriate to model pronunciation variation with syllable-length acoustic models than with context-dependent phones. Due to the large number of factors contributing to pronunciation variation at the syllable level, the creation of multi-path model topologies appears necessary. In this paper, we propose a novel approach for constructing multi-path models for frequent syllables. The suggested approach uses phonetic knowledge for the initialisation of the parallel paths, and a data-driven solution for their re-estimation. When applied to 94 frequent syllables in a 37-hour corpus of Dutch read speech, it leads to improved recognition performance when compared with a triphone recogniser of similar complexity.


doi: 10.21437/Interspeech.2006-442

Cite as: Hämäläinen, A., Bosch, L.t., Boves, L. (2006) Pronunciation variant-based multi-path HMMs for syllables. Proc. Interspeech 2006, paper 1630-Wed1BuP.8, doi: 10.21437/Interspeech.2006-442

@inproceedings{hamalainen06_interspeech,
  author={Annika Hämäläinen and Louis ten Bosch and Lou Boves},
  title={{Pronunciation variant-based multi-path HMMs for syllables}},
  year=2006,
  booktitle={Proc. Interspeech 2006},
  pages={paper 1630-Wed1BuP.8},
  doi={10.21437/Interspeech.2006-442}
}