Presenting in Virtual Worlds: An Architecture for a 3D Anthropomorphic Presenter
September/October 2006 (vol. 21 no. 5)
pp. 47-53
Multiparty-interaction technology is changing entertainment, education, and training. Deployed examples of such technology include embodied agents and robots that act as a museum guide, a news presenter, a teacher, a receptionist, or someone trying to sell you insurance, homes, or tickets. In all these cases, the embodied agent needs to explain and describe. This article describes the design of a 3D virtual presenter that uses different output channels (including speech and animation of posture, pointing, and involuntary movements) to present and explain. The behavior is scripted and synchronized with a 2D display containing associated text and regions (slides, drawings, and paintings) at which the presenter can point. This article is part of a special issue on interactive entertainment.
Index Terms:
multimodal generation, embodied conversational agents, virtual reality, presenting
Citation:
Herwin van Welbergen, Anton Nijholt, Dennis Reidsma, Job Zwiers, "Presenting in Virtual Worlds: An Architecture for a 3D Anthropomorphic Presenter," IEEE Intelligent Systems, vol. 21, no. 5, pp. 47-53, Sep./Oct. 2006, doi:10.1109/MIS.2006.101