This volume brings together the peer-reviewed contributions of the participants at the COST 2102 and euCognition International Training School on "Multimodal Signals: C- nitive and Algorithmic Issues" held in Vietri sul Mare, Salerno, Italy, April 22 -26, 2008. The school was sponsored by COST (European Cooperation in the Field of Scientific and Technical Research, www.cost.esf.org) in the domain of Information and Communi- tion Technologies (ICT) for disseminating the advances of the research activities developed within Action 2102: "Cross-Modal Analysis of Verbal and Nonverbal Communication" (www.cost.esf.org/domains_actions/ict/Actions/Verbal_and_Non- verbal _Communication) and by euCognition: The European Network for Advancement of Artificial Cognitive Systems (www.euCognition.org). COST Action 2102, in its second year of life, brought together about 60 European and 6 overseas scientific laboratories whose aim is to develop interactive dialogue systems and intelligent virtual avatars graphically embodied in a 2D and/or 3D int- active virtual world, able to interact intelligently with the environment, other avatars, and particularly with human users. The main theme of the school was to investigate the mathematical and psycholo- cal tools for modelling human-machine interaction through access to a graded series of tasks for measuring the amount of adjustment (as well as intelligence and achie- ment) needed for introducing new concepts in the information communication te- nology domain in order to develop adaptive, socially enabled and human-centered automatic systems able to serve remote applications in medicine, learning, care, re- bilitation, and for accessibility to work, employment, and information.
This book constitutes the thoroughly refereed post-conference
proceedings of the COST Action 2102 and euCognition supported international school on Multimodal Signals: "Cognitive and Algorithmic Issues" held in Vietri sul Mare, Italy, in April 2008.
The 34 revised full papers presented were carefully reviewed and selected from participants contributions and invited lectures given at the workshop. The volume is organized in two parts; the first on Interactive and Unsupervised Multimodal Systems contains 14 papers. The papers deal with the theoretical and computational issue of defining algorithms, programming languages, and determinist models to recognize
and synthesize multimodal signals. These are facial and vocal
expressions of emotions, tones of voice, gestures, eye contact, spatial arrangements, patterns of touch, expressive movements, writing patterns, and cultural differences, in anticipation of the implementation of intelligent avatars and interactive dialogue systems that could be exploited to improve user access to future telecommunication services. The second part of the volume, on Verbal and Nonverbal Communication Signals, presents 20 original studies devoted to the modeling of timing synchronisation between speech production, gestures, facial and head movements in human communicative expressions and on their mutual contribution for an effective communication.
