12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Language-Independent Socio-Emotional Role Recognition in the AMI Meetings Corpus

Fabio Valente (1), Alessandro Vinciarelli (2)

(1) Idiap Research Institute, Switzerland
(2) University of Glasgow, UK

Social roles are a coding scheme that characterizes the relationships between group members during a discussion and their roles "oriented toward the functioning of the group as a group". This work presents an investigation on language-independent automatic social role recognition in AMI meetings based on turns statistics and prosodic features. At first, turn-taking statistics and prosodic features are integrated into a single generative conversation model which achieves a role recognition accuracy of 59%. This model is then extended to explicitly account for dependencies (or influence) between speakers achieving an accuracy of 65%. The last contribution consists in investigating the statistical dependencies between the formal and the social role that participants have; integrating the information related to the formal role in the model, the recognition achieves an accuracy of 68%.

Full Paper

Bibliographic reference.  Valente, Fabio / Vinciarelli, Alessandro (2011): "Language-independent socio-emotional role recognition in the AMI meetings corpus", In INTERSPEECH-2011, 3077-3080.