Extracting deep bottleneck features for visual speech recognition

Chao Sui; Roberto Togneri; Mohammed Bennamoun

ICASSP 2015accepted0 citations

Extracting deep bottleneck features for visual speech recognition

Chao Sui, Roberto Togneri, Mohammed Bennamoun

Abstract

Motivated by the recent progresses in the use of deep learning techniques for acoustic speech recognition, we present in this paper a visual deep bottleneck feature (DBNF) learning scheme using a stacked auto-encoder combined with other techniques. Experimental results show that our proposed deep feature learning scheme yields approximately 24% relative improvement for visual speech accuracy. To the best of our knowledge, this is the first study which uses deep bottleneck feature on visual speech recognition. Our work firstly shows that the deep bottleneck visual feature is able to achieve a significant accuracy improvement on visual speech recognition.

BibTeX

@inproceedings{icassp2015_extractingdeepbo,
  title = {Extracting deep bottleneck features for visual speech recognition},
  author = {Chao Sui and Roberto Togneri and Mohammed Bennamoun},
  booktitle = {ICASSP 2015},
  year = {2015}
}