@inproceedings{HaqEtAl_AVSP08,
  author = {Haq, S. and Jackson, P.J.B. and Edge, J.},
  year = {2008},
  title = "Audio-visual feature selection and reduction for emotion classification",
  booktitle = "Proc.\ Int.\ Conf. on Auditory-Visual Speech Processing (AVSP'08), Tangalooma, Australia",
  month = {Sept.},
  abstract = 
"Recognition of expressed emotion from speech and facial gestures
was investigated in experiments on an audio-visual emotional
database. A total of 106 audio and 240 visual features
were extracted and then features were selected with Plus l-Take
Away r algorithm based on Bhattacharyya distance criterion. In
the second step, linear transformation methods, principal component
analysis (PCA) and linear discriminant analysis (LDA),
were applied to the selected features and Gaussian classifiers
were used for classification of emotions. The performance was
higher for LDA features compared to PCA features. The visual
features performed better than audio features, for both PCA
and LDA. Across a range of fusion schemes, the audio-visual
feature results were close to that of visual features. A highest
recognition rate of 53% was achieved with audio features,
98% with visual features, and 98% with audio-visual features
selected by Bhattacharyya distance and transformed by LDA."
}