Effective lip localization and tracking for achieving multimodal speech recognition

  title={Effective lip localization and tracking for achieving multimodal speech recognition},
  author={Wei Chuang Ooi and Changwon Jeon and Kihyeon Kim and David K. Han and Hanseok Ko},
  journal={2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems},
Effective fusion of acoustic and visual modalities in speech recognition has been an important issue in human computer interfaces, warranting further improvements in intelligibility and robustness. Speaker lip motion stands out as the most linguistically relevant visual feature for speech recognition. In this paper, we present a new hybrid approach to improve lip localization and tracking, aimed at improving speech recognition in noisy environments. This hybrid approach begins with a new color… CONTINUE READING


Publications referenced by this paper.

A new real-time lip contour extraction algorithm

  • 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).
  • 2003

Recent advances in the automatic recognition of audio - visual speech

Powers. D. M. Lewis. T. W
  • 2003

Automatic lip model extraction for constrained contour-based tracking

  • Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348)
  • 1999

A threshold selection method from graylevel histograms

S. L Wang, W. H Lau, S. H Leung
  • IEEE Trans . on Systems Man Cybernet
  • 1979