Generation of multi-modal dialogue for a net environment

Krenn, B.; Pirker, H.; Grice, M.; Baumann, S.; Piwek, P.; van Deemter, K.; Schroeder, M.; Klesen, M. and Gstrein, E. (2002). Generation of multi-modal dialogue for a net environment. In: Proceedings of KONVENS-02, 30 Sep - 02 Oct 2002, Saarbruecken, Germany.



In this paper an architecture and special purpose markup language for simulated affective face-to-face communication is presented. In systems based on this architecture, users will be able to watch embodied conversational agents interact with each other in virtual locations on the internet. The markup language, or Rich Representation Language (RRL), has been designed to provide an integrated representation of speech, gesture, posture and facial animation.

Viewing alternatives

Download history

Item Actions