logo Idiap Research Institute        
 [BibTeX] [Marc21]
Continuous Audio-Visual Speech Recognition
Type of publication: Conference paper
Citation: luettin-eccv98
Booktitle: Proc. 5th European Conference on Computer Vision
Series: Lecture Notes in Computer Science
Volume: II
Year: 1998
Publisher: Springer Verlag
Note: IDIAP-RR 98-02
Crossref: luettin-rr-98-02:
Abstract: We address the problem of robust lip tracking, visual speech feature extraction, and sensor integration for audio-visual speech recognition applications. An appearance based model of the articulators, which represents linguistically important features, is learned from example images and is used to locate, track, and recover visual speech information. We tackle the problem of joint temporal modelling of the acoustic and visual speech signals by applying Multi-Stream hidden Markov models. This approach allows the use of different temporal topologies and levels of stream integration and hence enables to model temporal dependencies more accurately. The system has been evaluated for a continuously spoken digit recognition task of 37 subjects.
Userfields: ipdmembership={vision},
Projects Idiap
Authors Luettin, Juergen
Dupont, St├ęphane
Added by: [UNK]
Total mark: 0
  • eccv98.pdf
  • luettin-eccv98.ps.gz