Mark Lucente, Gert-Jan Zwart, and Andrew George
The Visualization Space (VizSpace) is a visual computing system created as a testbed for deviceless multimodal user interfaces. Continuous voice recognition and passive machine vision provide two channels of interaction with computer graphics imagery on a wall-sized display. Users gesture (e.g., point) and speak commands to manipulate and navigate through virtual objects and worlds. Voiced commands are combined with several types of gestures -- full-body, deictic, symbolic and iconic -- to allow users to interact using only these natural human-to-human communication skills. The system is implemented on a single (high-end) IBM PC, yet provides comfortably interactive rates. It allows for rapid testing of voice/vision multimodal input and rapid prototyping of specific multimodal applications for natural interaction.