A statistical coarticulatory model for the hidden vocal-tract-resonance dynamics

  title={A statistical coarticulatory model for the hidden vocal-tract-resonance dynamics},
  author={Li Deng and Jeff Z. Ma},
A statistical coarticulatory model is presented for spontaneous speech recognition, where knowledge of the dynamic, target-directed behavior in the vocal tract resonance responsible for the production of highly coarticulated speech is incorporated into the recognizer design, training, and in likelihood computation. The principal advantage of the new speech model over the conventional HMM is the use of a compact, internal structure that parsimoniously represents long-span context dependence in… CONTINUE READING
Highly Cited
This paper has 39 citations. REVIEW CITATIONS
22 Citations
9 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 22 extracted citations


Publications referenced by this paper.
Showing 1-9 of 9 references

Coarticulation modeling with continuous-state HMMs,

  • R. Bakis
  • Proc. IEEE Workshop Automatic Speech Recognition,
  • 1991
Highly Influential
5 Excerpts

From HMMs to segment models: A uni ed view of stochastic modeling for speech recognition

  • M. Ostendorf
  • IEEE Trans. Speech Audio Proc.,
  • 1996

Stochastic Processes and Filtering

  • A. H. Jazwinski
  • 1970

Similar Papers

Loading similar papers…