BEAT: The Behavior Expression Animation Toolkit
Gesture and Narrative Language group

Researchers:		Prof. Justine Cassell Hannes Högni Vilhjálmsson and Timothy Bickmore
Project Web site:		http://www.media.mit.edu/gnl/projects/beat/
Group Web site:		http://gn.www.media.mit.edu/groups/gn/

Animators type into this system dialogue to be spoken by an animated human figure. BEAT then determines appropriate speech characteristics and actions to be performed by the character as it is speaking, resulting in a more realistic and human-like character.

Nonverbal behaviors (such as shrugs or hand gestures) are assigned on the basis of actual linguistic and contextual analysis of the typed text, relying on rules derived from extensive research into human conversational behavior.

The toolkit is extensible, so that new rules can be added quickly. It is designed to plug into larger systems that also may assign personality profiles, motion characteristics, scene constraints, or the animation styles of particular animators.

	TTT sponsors have access to more project details in the Sponsor section of the site. Learn more here.