Levels of Representation in the Annotation of Emotion for the Specification of Expressivity in ECAs

Abstract

In this paper we present a two-steps approach towards the creation of affective Embodied Conversational Agents (ECAs): annotation of a real-life non-acted emotional corpus and animation by copy-synthesis. The basis of our approach is to study how coders perceive and annotate at several levels the emotions observed in a corpus of emotionally rich TV video interviews. We use their annotations to specify the expressive behavior of an agent at several levels. We explain how such an approach can be useful for providing knowledge as input for the specification of non-basic patterns of emotional behaviors to be displayed by the ECA (e.g. which perceptual cues and levels of annotation are required for enabling the proper recognition of the emotions).

Survey and Evaluation of Mpeg-4 Based 3D Character Animation Frameworks

“…In future developments we intend to aggregate more information about these frameworks and to create a system which permits to convert video recording from a speaker to MPEG-4 FBA specification to achieve a more complete evaluation, by comparing real footage with synthetic generated one. Similar work was completed for Greta [30].…”

Persuasion and the expressivity of gestures in humans and machines

“…We have conducted a study using EmoTV, a corpus of real data made of video clips from French TV news (Martin et al 2006). The people interviewed in the video clips showed complex emotions, which might arise from the evaluation of the same event from different perspectives (Scherer 2000;Devillers et al, 2005). Emotion labels, behaviour descriptions and expressivity dimensions were annotated.…”

Perception of Blended Emotions: From Video Corpus to Expressive Agent

“…The "multiple levels replay" approach involves the level of annotation of emotions, and the low-level annotations of multimodal behaviors (such as the gesture expressivity for assigning values to the expressivity parameters of the ECA, and the manual annotation of facial expressions) [25]. The "facial blending replay" approach is identical to the "multiple levels replay" approach except for facial expressions: it uses a computational model for generating facial expressions of blend of emotions [25]. More details are provided below on how these two approaches have been used in our perceptual study.…”