Audio-visual speech modeling using coupled hidden Markov models

  title={Audio-visual speech modeling using coupled hidden Markov models},
  author={Stephen M. Chu and Thomas S. Huang},
  journal={2002 IEEE International Conference on Acoustics, Speech, and Signal Processing},
In this work we consider the bimodal fusion problem in audio-visual speech recognition. A novel sensory fusion architecture based on the coupled hidden Markov models (CHMMs) is presented. CHMMs are directed graphical models of stochastic processes and are a special type of dynamic Bayesian networks. The proposed fusion architecture allows us to address the statistical modeling and the fusion of audio-visual speech in a unified framework. Furthermore, the architecture is capable of capturing the… CONTINUE READING
Highly Cited
This paper has 33 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 23 extracted citations

Similar Papers

Loading similar papers…