CONTACT: A Multimodal Corpus for Studying Expressive Styles and Informing the Design of Individualized Virtual Narrators

Abstract

Virtual agents used in storytelling applications should display consistent and natural multimodal expressions of emotions. In this paper, we describe the method that we defined to endow virtual narrators with individual gesture profiles. We explain how we collected a corpus of gestural behaviors displayed by different actors telling the same story. Videos were annotated both manually and automatically. Preliminary analyses are presented.