In recent years, 3D talking heads have become a popular subject in both research and industry domains. As the powerful hardware for 3D rendering become available in regular desktops, state of the art realtime rendering and animation techniques is much easier to accomplish.

We have started an open source initiative which provide the research community a free and open source tool for generating and animating 3D talking agents, namely Xface (Balci 2005). Xface toolkit relies on MPEG-4 standard for facial animation, so that it is able to playback standard MPEG-4 FAP (Facial Animation Parameters) streams.

Synthetic characters are an effective modality to convey messages to the user, provide visual feedback about the system internal understanding of the communication, and engage the user in the dialogue through emotional involvement. A fine-grain distinction of the expressive capabilities of synthetic agents is necessary to fully exploit the communicational power: avatars should not be considered as an indivisible modality but as the synergic contribution of different communication channels that, properly synchronized, generate an overall communication performance. In this view, we propose SMIL-AGENT (Not et al., 2005) as a representation and scripting language for synthetic characters, which abstracts away from the specific implementation and context of use of the character. SMIL-AGENT has been defined starting from SMIL 0.1 standard specification and aims at providing a high-level standardized language for presentations by different synthetic agents within diverse communication and application contexts.

We are also investigating the recognizability of the various traits of an ECA and its effect on the human-computer interaction. We developed DaFex a database of kinetic human facial expressions of more than 1000 videos from 8 professional actors; each actor played the 7 Ekman's emotions with 3 different level of intensity. The database has been used in a number of controlled experiments and it is now available to the research community.

People

Alberto Battocchi

Koray Balci

Nadia Mana

Elena Not

Fabio Pianesi

Massimo Zancanaro

Publications

Mana N., Pianesi F., Modelling of Emotional Facial Expressions during Speech in Synthetic Talking Heads using a Hybrid Approach. In Proceedings of AVSP2007, International Conference on Auditory-Visual Speech Processing, Hilvarenbeek (The Netherlands), 31 August-3 September, 2007.(pdf)

Mana N., Pianesi F., HMM-based synthesis of emotional facial expressions during speech in synthetic talking heads. In Proceedings of ICMI'06, Banff 2006.(pdf)

Mana N., Cosi P., Tisato G., Cavicchio F., Magno E. and Pianesi F., An Italian Database of Emotional Speech and Facial Expressions, In Proceedings of "Workshop on Emotion: Corpora for Research on Emotion and Affect", in association with "5th International Conference on Language, Resources and Evaluation (LREC2006), Genoa, Italy, 24-25-26 May 2006.(pdf)

Not E., Balci K., Pianesi F., Zancanaro M., Synthetic characters as multichannel interfaces. In Proceedings of ICMI'05, Trento 2005. (pdf)

Balci, K. Xface: MPEG-4 based open source toolkit for 3d facial animation. In Proceedings of AVI04, Working Conference on Advanced Visual Interfaces. Gallipoli, Italy, 25-28 May, 2004. (pdf)