ISCA Archive ICSLP 1998
ISCA Archive ICSLP 1998

The voicing feature for stop consonants: acoustic phonetic analyses and automatic speech recognition experiments

Padma Ramesh, Partha Niyogi

We examine the distinctive feature [voice] that separates the voiced from the unvoiced sounds for the case of stop consonants. We conduct acoustic phonetic analyses on a large database and demonstrate the superior separability using a temporal measure (voice onset time; VOT) rather than spectral measures. We describe several algorithms to automatically estimate the VOT from continuous speech and compare them on a speech recognition problem to reduce error rates by as much as 53 percent over a baseline HMM based system.


doi: 10.21437/ICSLP.1998-562

Cite as: Ramesh, P., Niyogi, P. (1998) The voicing feature for stop consonants: acoustic phonetic analyses and automatic speech recognition experiments. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0881, doi: 10.21437/ICSLP.1998-562

@inproceedings{ramesh98_icslp,
  author={Padma Ramesh and Partha Niyogi},
  title={{The voicing feature for stop consonants: acoustic phonetic analyses and automatic speech recognition experiments}},
  year=1998,
  booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
  pages={paper 0881},
  doi={10.21437/ICSLP.1998-562}
}