IVAN - Intelligent Interactive Virtual Agent Narrators

Multimodal user interfaces are becoming more and more important in humann machine communication. Essential representatives of such interfaces are virtual agents that aim to act like humans in the way they employ gestures, facial expression, posture and prosody to convey their emotions in face-to-face communication. Furthermore, if we employ a presentation team [1] to convey facts, the performance becomes more entertaining for the audience. Distinct characters should have different roles and personality profiles. Moreover if we integrate interaction capabilities for the user, the system becomes more personalized and enjoyable. The GALA challenge is to provide behaviourally complex, affective commentary on a continuous event in real-time. Two approaches for implementing such a commentary agent are: plan-based and rule-based. An example of a rule-based agent is ERIC [2], developed at DFKI. While ERIC was a monologic system, we integrate two commentators, therefore dialogue planning offers itself as the best strategy.