SIGNE project: Virtual humanoid endowed with expressive gestures - Application to analysis and synthesis of French Sign Language
This work has been done in collaboration with the M2S lab., University of Rennes.Participants: Alexis Héloir (PhD student 2004-2007, SAMSARA), Sylvie Gibet (Advisor, SAMSARA), Franck Multon (co-advisor, M2S), Nicolas Courty (SAMSARA)
Acknowledgements: This work was made possible by Award of the Région Bretagne, France
Keywords : Animation, Virtual Character, Gestural Communication, Sign Language, Style Translation
Get the Flash Player to see this player.
The originality of this work consists in analysing the expressiveness of generated communicative gestures, as well as as well as characterizing the symbolic representations of such gestures. Our analysis/synthesis framework allows us to exploit richness of existing gestures while enabling a parametrization of those gestures. This method is applied on a subset of French Sign Language (FSL) gestures.
Captured gesture sequences
neutral , tough , wearyTemporal alignment of communicative gesture sequences
temporal deformation
Among the different problems related to editing motion data, style translation has drawn particular attention. In this video we address the problem of motion temporal alignment applied to captured communicative gestures conveying different styles (here neutral and nervous moods). This alignment process is actually used to translate a motion from one style to another [casa 2006, best selected paper].
References
[1] Héloir A. Système de communication par agents virtuels - Aide à la communication des personnes sourdes, Thèse de PhD, Université de Bretagne Sud, Vannes, janv. 2008.
[2] A. Héloir, N. Courty, S. Gibet, et F. Multon. Temporal alignment of communicative gesture sequences. Computer Animation and Virtual Worlds (selected best papers from CASA'06), 17:347357, juillet 2006.
[3] S. Gibet, A. Héloir, N. Courty, J.-F. Kamp P. Gorce, N. Rezzoug, F. Multon, et C. Pelachaud. Virtual agent for deaf signing gestures. AMSE, Journal of the Association for the Advancement of Modelling and Simulation Techniques in Enterprises (Special edition HANDICAP), 2006.
[4] Héloir A., Gibet S., Multon F., Courty N. Captured Motion Data Processing for Real-Time Synthesis of Sign Language. In Gesture in Human-Computer Interaction and Simulation, Springer, to appear.
[5] Gibet, S & Marteau, P.F., A Self-organisedMmodel for the Control, Planning and Learning of Nonlinear Multivariable Systems using a Sensori Feedback, Journal of Applied Intelligence, Springer / Kluwer Academic Publisher, vol 4, Boston, pp.337-349, 1994.
[6] Lebourque T., Synthèse de gestes de la langue des signes française, PhD thesis, University of Paris XI, Orsay, Nov. 1998.
[7] Lebourque T. & Gibet S. High level specification and control of communication gestures: the GESSYCA System, Computer Animation 1999, Computer Graphics Society (CGS) & IEEE Computer Society, Geneva, 26-28 mai 1999.
[8] Gibet S. & Lebourque T. High level Specification and Animation of Communicative Gestures, Journal of Visual Languages and Computing, 12, 657-687, 2001.