Exploiting transitions and focussing on linguistic properties for ASR

  title={Exploiting transitions and focussing on linguistic properties for ASR},
  author={Jacques C. Koreman and William J. Barry and Bistra Andreeva},
This paper describes three cross-language ASR experiments which use hidden Markov mode lling. The first one shows that consonant identification improves when vowel transitions are used. In particular, the consonants’ place of articulation is identified better, because the vowel transitions contain formant trajectories which depend on the consonant’s place of articulation. The second experiment compares consonant identification results when acoustic parameters belonging to the consonant itself… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 15 references

A signal representation of speech based on phonetic features

  • N. Bitar, C. Espy-Wilson
  • Proc. 5th Annual Dual-Use Techn. and Applications…
  • 1995
1 Excerpt

The place of articulation distinction in voiced oral stops: evidence from burst spectra and formant transitions

  • S Cassidy, J. Harrington
  • Phonetica
  • 1995

Phoneme label alignment using acoustic-phonetic features and Gaussian probab ility density functions

  • P. Dalsgaard
  • Computer Speech and Language
  • 1992
1 Excerpt

Modeling acoustic-phonetic detail in an HMMbased large vocabulary speech recognizer

  • L. Deng, M. Lennig, V. Gupta, P. Mermelstein
  • Proc. IEEE Int. Conf. on Acoustics, Speech, and…
  • 1988
1 Excerpt

Context-dependent phonetic Markov models for large vocabulary speech recogn ition

  • Derouault, A.-M
  • Proc. IEEE Int. Conf. on Acoustics, Speech, and…
  • 1987
1 Excerpt

Context-dependent modeling for acoustic-phonetic recogn ition of continuous speech

  • R. Schwartz, Y. Chow, O. Kimball, S. Roucos, M. Krasner, J. Makhoul
  • Proc. IEEE Int. Conf. on Acoustics,
  • 1985
1 Excerpt

Similar Papers

Loading similar papers…