Towards natural gesture synthesis: Evaluating gesture units in a data-driven approach to gesture synthesis
Intelligent Virtual Agents: 7th International Conference, IVA 2007 Paris …, 2007•Springer
Virtual humans still lack naturalness in their nonverbal behaviour. We present a data-driven
solution that moves towards a more natural synthesis of hand and arm gestures by
recreating gestural behaviour in the style of a human performer. Our algorithm exploits the
concept of gesture units to make the produced gestures a continuous flow of movement. We
empirically validated the use of gesture units in the generation and show that it causes the
virtual human to be perceived as more natural.
solution that moves towards a more natural synthesis of hand and arm gestures by
recreating gestural behaviour in the style of a human performer. Our algorithm exploits the
concept of gesture units to make the produced gestures a continuous flow of movement. We
empirically validated the use of gesture units in the generation and show that it causes the
virtual human to be perceived as more natural.
Abstract
Virtual humans still lack naturalness in their nonverbal behaviour. We present a data-driven solution that moves towards a more natural synthesis of hand and arm gestures by recreating gestural behaviour in the style of a human performer. Our algorithm exploits the concept of gesture units to make the produced gestures a continuous flow of movement. We empirically validated the use of gesture units in the generation and show that it causes the virtual human to be perceived as more natural.
Springer
