Item

Abstract

This paper describes the implementation of an automatically generated virtual storyteller from fairy tale texts
which were previously annotated for emotion. In order to gain insight into the effectiveness of our virtual storyteller we recorded face, body and voice of an amateur actor and created an actor animation video of one of the
fairy tales. We also got the actor's annotation of the fairy tale text and used this to create a virtual storyteller video. With these two videos, the virtual storyteller and the actor animation, we conducted a user study to determine the effectiveness of our virtual storyteller at conveying the intended emotions of the actor. Encouragingly, participants performed best (when compared to the intended emotions of the actor) when they marked the emotions of the virtual storyteller. Interestingly, the actor himself was not able to annotate the animated actor video with high accuracy as compared to his annotated text. This argues that for future work we must have our actors also annotate their body and facial expressions, not just the text, in order to further investigate the effectiveness of our virtual storyteller. This research is a first step towards using our virtual storyteller in real-time immersive virtual environments.