Audio-Visual Speech Modeling for Continuous Speech Recognition

  title={Audio-Visual Speech Modeling for Continuous Speech Recognition},
  author={St{\'e}phane Dupont and Juergen Luettin},
  journal={IEEE Trans. Multimedia},
This paper describes a speech recognition system that uses both acoustic and visual speech information to improve the recognition performance in noisy environments. The system consists of three components: 1) a visual module; 2) an acoustic module; and 3) a sensor fusion module. The visual module locates and tracks the lip movements of a given speaker and extracts relevant speech features. This task is performed with an appearance-based lip model that is learned from example images. Visual… CONTINUE READING
Highly Influential
This paper has highly influenced 66 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 550 citations. REVIEW CITATIONS
347 Citations
49 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 347 extracted citations

551 Citations

Citations per Year
Semantic Scholar estimates that this publication has 551 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 49 references

Connectionist Speech Recognition—A Hybrid Approach

  • H. Bourlard, N. Morgan
  • Norwell, MA: Kluwer,
  • 1994
Highly Influential
3 Excerpts

A Multi-Band Approach to Automatic Speech Recognition,

  • N. N. Mirghafori
  • Ph.D. dissertation, Int. Comput. Sci. Inst.,
  • 1999
1 Excerpt

Similar Papers

Loading similar papers…