On Development of a Gesture Plug-in for Natural Dialogue Systems

This paper describes work in progress on the development of a plugin automatic gesture recogniser intended for a human-computer natural speechand-gesture dialogue interface module. A model-based approach is suggested for the gesture recognition. Gesture models are built from models of selected finger tip trajectories as traversed through physical 3D space of the human gesturer when performing the different gestures of interest. Gesture capture employs in the initial version a data glove, later computer vision is intended. The paper outlines at a general level the gesture model design and argues for its choice, as well as the rationale behind the entire work is laid forth. As the recogniser is not yet fully implemented no test results can be presented so far.