Auditory-Visual Speech Processing (AVSP) 2011

Volterra, Italy
September 1-2, 2011

“Mask-bot” - A Life-Size Talking Head Animated Robot for AV Speech and Human-Robot Communication Research

Takaaki Kuratate (1,2), Brennard Pierce (1), Gordon Cheng (1)

(1) Institute for Cognitive Systems, Technical University Munich, Germany
(2) MARCS Auditory Laboratories, University of Western Sydney, Australia

In this paper we introduce our life-size talking head robotic system, Mask-bot, developed to support human-robot communication research. The physical system consists of a semitransparent face mask, a portable LED projector with a fish-eye conversion lens, a pan-tilt unit and a mounting base. Mask-bot uses the mask as a screen for a talking head animation engine that is broadcast from the projector mounted behind the mask. Via this process the head becomes a life-size talking head in real space as opposed to 2D flat screen space or stereo pseudo-3D screen space, affording the means for testing new face models for AV speech synthesis and perception in life-size output without building an actual robotic head.

Index Terms. talking head, face animation, AV speech synthesis, 3D face model, humanoid robot, robotic head

Full Paper

Bibliographic reference.  Kuratate, Takaaki / Pierce, Brennard / Cheng, Gordon (2011): "“mask-bot” - a life-size talking head animated robot for AV speech and human-robot communication research", In AVSP-2011, 111-116.