In the afternoon of Monday, 23 November 2015, Imagine and CRISSP (GIPSA-lab) organize a seminar on Expressive virtual actors. This event is a special session in the series supported by the ERC Expressive, and follows the PhD defense of Adela Barbulescu in the morning of the same day.
The seminar will be held in the Amphi E of ENSIMAG (see map) in the Grenoble campus, with the beginning scheduled for 13:30.
Everyone is welcome!
Tentative Schedule
13:30 — 14:00
Slim Ouni (University of Lorraine)
Toward Realistic Expressive Audiovisual Speech Synthesis
14:00 — 14:30
Catherine Pelachaud (Telecom Paris Tech)
Interacting with socio-emotional embodied conversational agent
14:30 — 15:00
Ronan Boulic (EPFL)
Real-Time Posture Semantics Mapping in Performance Animation
14:30 — 15:00
Marc Swerts (Tillburg University)
On the elicitation and perception of facial cues to surprise
Slim Ouni : Toward Realistic Expressive Audiovisual Speech Synthesis
In this talk, we present our ongoing work on developing an expressive audiovisual speech synthesis. Currently, we are focusing on developing multimodal acquisition techniques that allow acquiring both speech related gestures and facial expression gestures. One of our concerns in this work is to develop a realistic face where the facial animation is realistic, as observed in humans.
Slim Ouni is an associate professor (hdr) at Université de Lorraine. He obtained his HDR in 2013, and a PhD in Computer Science in 2001. His main research interests are audiovisual speech synthesis, speech production, articulatory modeling, and audiovisual speech intelligibility.
Catherine Pelachaud : Interacting with socio-emotional embodied conversational agent
In this talk I will present our current work toward endowing virtual agents with socio-emotional capabilities. By applying different methodologies, based on corpus analysis, user-centered, or motion capture, we have enriched the agent’s palette of multimodal behaviors. We have conducted various studies to simulate communicative behaviors, emotional behaviors, social attitudes and behavior expressivity. Through its behaviors patterns, the agent can communicate with different social attitudes; its relationship towards its interlocutors influence how it behaves and places itself while conversing with them.
Catherine Pelachaud is a Director of Research at CNRS in the laboratory LTCI, TELECOM ParisTech. Her research interest includes embodied conversational agent, nonverbal communication (face, gaze, and gesture), expressive behaviors and socio-emotional agents. She is associate editors of several journals among which IEEE Transactions on Affective Computing, ACM Transactions on Interactive Intelligent Systems and Journal on Multimodal User Interfaces. She has co-edited several books on virtual agents and emotion-oriented systems.
Ronan Boulic : Real-Time Posture Semantics Mapping in Performance Animation
left: live, middle: without our technique, right: with the egocentric mapping.In this work, mostly conducted by Eray Molla during his PhD thesis, we addressed the problem of real-time mapping of a user posture onto a target character with human-like topology but with potentially different size, volume and proportions. We propose a posture normalization technique allowing to preserve the relative location of body parts with respect to each other, including the limb ordering in complex postures such as crossed arm or legs. These properties allow to implicitly transfer the semantic of a large range of body postures and reduce significantly the cognitive load of the performer as the mapping is quasi transparent. The performer can then focus on the truly expressive dimension of the performance. Such technique can be used to speedup the production of animations or for live performances (theme park etc).
Ronan Boulic is a Senior Scientist and PhD Advisor at the EPFL (Ecole Polytechnique Fédérale de Lausanne). He currently leads the Immersive Interaction research group (IIG) from the School of Computer and Communication Sciences. He received the PhD degree in Computer Science in 1986 from the University of Rennes, France, and the Habilitation degree in Computer Science from the University of Grenoble, France, in 1995. He is senior member of IEEE and of ACM, and member of Eurographics. Ronan Boulic has co-authored more than 140 refereed publications, including 36 in ISI-indexed journals, and contributed to 10 books. He was paper co-chair of the Eurographics/SIGGRAPH Symposium on Computer Animation 2004 in Grenoble, and general chair of the same symposium in 2012 in Lausanne. He was also paper co-chair of the joint Virtual Reality conference JVRC in Madrid in 2012. He has served on over 50 program committees of key conferences in computer graphics, computer animation and virtual Reality. His fields of interest include 3D interactions, motion capture, modeling, and synthesis for virtual humans and robots, virtual reality and embodiment.
Marc Swerts : On the elicitation and perception of facial cues to surprise
Many people have argued that people tend to produce specific facial expressions when they are exposed to an unexpected event. A full facial display of “surprise” has often been defined as consisting of a combination of three features: someone who is surprised will raise his or her eyebrows, open his or her mouth and widen his or her eyes. However, when researchers try to elicit the expression of surprise with participants, this prototypical display is rarely shown. To gain further insight into this, we have set a specific paradigm which attempts to spontaneously elicit cues to surprise, and also tests to what extent these expressions can reliably be interpreted by independent observers.
Marc Swerts is a full professor in the Department of Communication and Information Science of the School of Humanities at Tilburg University (The Netherlands). He is a member of the TiCC research center of Cognition and Communication, and, together with Emiel Krahmer, leads the Language, Communication, and Cognition (LCC) research group in that center. His scientific focus is on trying to get a better understanding of how speakers exploit nonverbal features to exchange information with their addressees. He is particularly interested in the interplay between prosodic characteristics, facial expressions and gestures to signal socially and linguistically relevant information. He has served on the editorial board of three major journals in the field of language and speech research, and have been the editor-in-chief of Speech Communication. He was elected to become one of the two distinguished lecturers (for the years 2007-2008) of the International Speech Communication Association (ISCA) to promote speech research in various parts of the world.
