Information Theoretic Feature Extraction for Audio-Visual Speech Recognition

  title={Information Theoretic Feature Extraction for Audio-Visual Speech Recognition},
  author={Mihai Gurban and Jean-Philippe Thiran},
  journal={IEEE Transactions on Signal Processing},
The problem of feature selection has been thoroughly analyzed in the context of pattern classification, with the purpose of avoiding the curse of dimensionality. However, in the context of multimodal signal processing, this problem has been studied less. Our approach to feature extraction is based on information theory, with an application on multimodal classification, in particular audio-visual speech recognition. Contrary to previous work in information theoretic feature selection applied to… CONTINUE READING
Highly Cited
This paper has 62 citations. REVIEW CITATIONS


Publications citing this paper.

63 Citations

Citations per Year
Semantic Scholar estimates that this publication has 63 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 44 references

Audio-visual automatic speech recognition: An overview

  • G. Potamianos, C. Neti, J. Luettin, I. Matthews
  • Issues in Audio-Visual Speech Processing, G…
  • 2004
Highly Influential
5 Excerpts

Similar Papers

Loading similar papers…