Towards Speaker Independent Continuous Speechreading

This paper describes recent speechreading experiments for a speaker independent continuous digit recognition task. Visual feature extraction is performed by a lip tracker which recovers information about the lip shape and information about the grey-level intensity around the mouth. These features are used to train visual word models using continuous density HMMs. Results show that the method generalises well to new speakers and that the recognition rate is highly variable across digits as expected due to the high visual confusability of certain words.


Published in:
Proceedings of the European Conference on Speech Communication and Technology, 1991-1994
Presented at:
Proceedings of the European Conference on Speech Communication and Technology
Year:
1997
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)