Conference paper
Automated lip synchronisation for human-computer interaction and special effect animation
Proceedings of the IEEE International Conference on Multimedia Computing and Systems, pp.589-596
IEEE International Conference on Multimedia Computing and Systems, 1997 (Ottawa, Canada, 03-Jun-1997–06-Jun-1997)
IEEE (Institute of Electrical and Electronics Engineers)
1997
Abstract
The research presents MARTI (Man-machine Animation Real-Time Interface) for the realisation of automated special effect animation and human computer interaction. MARTI introduces novel research in a number of engineering disciplines, which include speech recognition, facial modelling, and computer animation. This interdisciplinary research utilises the latest, hybrid connectionist/hidden Markov model system, providing very accurate phone recognition and timing for speaker independent continuous speech, and expands' knowledge from the animation industry in the development of accurate facial models and automated animation. The system uses simple vocal soundtracks of human speakers to provide lip synchronisation of computer graphical facial models, to realise the first natural interface and animation system capable of high performance for real users and real-world applications.
Details
- Title
- Automated lip synchronisation for human-computer interaction and special effect animation
- Authors
- Christian M Jones (Author) - University of Newcastle upon Tyne, United KingdomS S Dlay (Author) - University of Newcastle upon Tyne, United Kingdom
- Publication details
- Proceedings of the IEEE International Conference on Multimedia Computing and Systems, pp.589-596
- Conference details
- IEEE International Conference on Multimedia Computing and Systems, 1997 (Ottawa, Canada, 03-Jun-1997–06-Jun-1997)
- Publisher
- IEEE (Institute of Electrical and Electronics Engineers)
- Date published
- 1997
- DOI
- 10.1109/MMCS.1997.609773
- ISBN
- 01818678194
- Organisation Unit
- School of Social Sciences - Legacy; University of the Sunshine Coast, Queensland; Engage Research Lab; School of Law and Society
- Language
- English
- Record Identifier
- 99449356202621
- Output Type
- Conference paper
Metrics
1 File views/ downloads
788 Record Views