This paper presents two examples of how nonverbal commu- nication can be automatically detected and interpreted in terms of social phenomena. In particular, the presented approaches use simple prosodic features to distinguish between journalists and non-journalists in media, and extract social networks from turn-taking to recognize roles in dif- ferent interaction settings (broadcast data and meetings). Furthermore, the article outlines some of the most interesting perspectives in this line of research.
Hervé Bourlard, Philip Neil Garner, Milos Cernak, Afsaneh Asaei, Pierre-Edouard Jean Charles Honnet