Classifying visemes for automatic lipreading

Visser, M. and Poel, M. and Nijholt, A. (1999) Classifying visemes for automatic lipreading. In: International Workshop Text, Speech and Dialogue (TSD'99), 13-17 September, 1999, Plzen, Czech republic.

PDF
Restricted to UT campus only: Request a copy
64Kb

Abstract:	Automatic lipreading is automatic speech recognition that uses only visual information. The relevant data in a video signal is isolated and features are extracted from it. From a sequence of feature vectors, where every vector represents one video image, a sequence of higher level semantic elements is formed. These semantic elements are "visemes" the visual equivalent of "phonemes" The developed prototype uses a Time Delayed Neural Network to classify the visemes.
Item Type:	Conference or Workshop Item
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Human Media Interaction (HMI)
Link to this item:	http://purl.utwente.nl/publications/64013
Official URL:	http://dx.doi.org/10.1007/3-540-48239-3_65
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page