Towards Natural Gesture Synthesis: Evaluating Gesture Units in a Data-Driven Approach to Gesture Synthesis

Don’t Scratch! Self-adaptors Reflect Emotional Stability

“…They used fixed poses to accompany hand scripted utterances, rather than a multimodal agent. Kipp et al [21] demonstrated that gesture units consisting of multiple gestures performed better than singleton gestures on a variety of criteria such as naturalness and friendliness and found singleton gestures appeared more nervous. Our work is the first we are aware of to address the combined verbal and nonverbal expression of emotional stability.…”

Multimodal Human Machine Interactions in Virtual and Augmented Reality

“…The complexity of the communicative act should be taken into account in human-computer interaction research aiming at modeling and improving such interaction by developing user-friendly applications which should simplify and enrich the end user's ability to interact with automatic systems. Psycholinguistic studies [26,25,43,52,56] have confirmed the complementary nature of verbal and nonverbal aspects in human expressions, demonstrating how visual information processing integrates and supports the comprehension of messages. In the light of these results, several research works on mutual contribution of speech and gesture in communication and on their characteristics have being carried out also in the field of Human Machine Interaction (HMI).…”

“…To animate an ECA procedural animation is often chosen over motion capture technique. The representation of co-verbal gestures in ECAs follows the literature on communicative gesture [43]. A gesture is divided into phases: preparation, pre-hold-stroke, stroke, post-stroke-hold and retraction [43].…”

“…The representation of co-verbal gestures in ECAs follows the literature on communicative gesture [43]. A gesture is divided into phases: preparation, pre-hold-stroke, stroke, post-stroke-hold and retraction [43]. Several systems use the approach proposed by Liddell [48] to describe arm position and hand shape for American Sign Language.…”

Some Pitfalls for Developing Enculturated Conversational Agents

“…Over the last decade, numerous work has established the area of multimodal corpus analysis to shed light on the specifics of multimodal interaction. To give some examples, [16] suggest an annotation scheme for gestures that draws on the distinction between the temporal course of a gesture and its type and relies on a gesture typology introduced by [20]. [1] as well as [7] annotate instead the expressivity dimensions of gestural activity focusing on how a gesture is accomplished and not on what kind of gesture is used.…”