ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Investigating phonetic information reduction and lexical confusability

William Hartmann, Eric Fosler-Lussier

In the presence of pronunciation variation and the masking effects of additive noise, we investigate the role of phonetic information reduction and lexical confusability on ASR performance. Contrary to previous work [1], we show that place of articulation as a representation for unstressed segments performs at least as well as manner of articulation in the presence of additive noise. Methods of phonetic reduction introduce lexical confusibility which negatively impact performance. By limiting this confusability, recognizers that employ high levels of phonetic reduction (40.1%) can perform as well a baseline system in the presence of nonstationary noise.

E. J. Briscoe, “Lexical access in connected speech recognition.” Proceedings of the 27th Annual Meeting of the Association for Computational Linguists, 1989, pp. 84–90.


doi: 10.21437/Interspeech.2009-503

Cite as: Hartmann, W., Fosler-Lussier, E. (2009) Investigating phonetic information reduction and lexical confusability. Proc. Interspeech 2009, 1659-1662, doi: 10.21437/Interspeech.2009-503

@inproceedings{hartmann09_interspeech,
  author={William Hartmann and Eric Fosler-Lussier},
  title={{Investigating phonetic information reduction and lexical confusability}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={1659--1662},
  doi={10.21437/Interspeech.2009-503}
}