Statistical lip modelling for visual speech recognition

We describe a speechreading (lipreading) system purely based on visual features extracted from grey level image sequences of the speakers lips. Active shape models are used to track the lip contours while visual speech information is extracted from the shape of the contours. The distribution and temporal dependencies of the shape features are modelled by continuous density Hidden Markov Models. Experiments are reported for speaker independent recognition tests of isolated digits. The analysis of individual feature components suggests that speech relevant information is embedded in a low dimensional space and fairly robust to inter- and intra- speaker variability.


Published in:
Proceedings of the 8th European Signal Processing Conference (Eusipco'96), I, 137-140
Presented at:
Proceedings of the 8th European Signal Processing Conference (Eusipco'96)
Year:
1996
Keywords:
Laboratories:




 Record created 2006-03-10, last modified 2018-03-17

n/a:
Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)