We demonstrate a novel method for producing a synthetic talking head. The method is based on earlier work in which the behaviour of a synthetic individual is generated by reference to a probabilisticmodel of interactive behaviour within the visual domain - such models are learnt automatically from typical interactions. We extend this work into a combined visual and auditory domain and employ a state-of-the-art facial appearance model. The result is a synthetic talking head that responds appropriately and with correct timing to simple forms of greeting with variations in facial expression and intonation. keywords : interactive head, face tracking, speech reconstitution, virtual partner, behaviour modelling.
Vincent E. Devin, David Hogg