Audio-visual speech processing: progress and challenges

Authors:
Gerasimos Potamianos
Affiliations:
IBM Thomas J. Watson Research Center, Yorktown Heights, NY
Venue:
VisHCI '06 Proceedings of the HCSNet workshop on Use of vision in human-computer interaction - Volume 56
Year:
2006

Citing 2
Cited 1

Photo-realistic talking-heads from image samples

IEEE Transactions on Multimedia
A review of speech-based bimodal recognition

IEEE Transactions on Multimedia

Integration of face detection and user identification with visual speech recognition

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part V

Quantified Score

Hi-index	0.00

Visualization

Abstract

This keynote focuses on using visual channel information to improve automatic speech processing for human computer interaction. Two main issues are discussed: the extraction and representation of visual speech, as well as its fusion with traditional acoustic information. The talk mostly considers applying these techniques to automatic speech recognition, however additional areas of interest are also mentioned, for example audio-visual speech detection, enhancement, and synthesis, as well as speaker recognition. The state-of-the-art and remaining challenges in these areas are also discussed.