Sciweavers

Share
MM
2009
ACM

Automatic role recognition in multiparty recordings using social networks and probabilistic sequential models

9 years 11 months ago
Automatic role recognition in multiparty recordings using social networks and probabilistic sequential models
The automatic analysis of social interactions is attracting significant interest in the multimedia community. This work addresses one of the most important aspects of the problem, namely the recognition of roles in social exchanges. The proposed approach is based on Social Network Analysis, for the representation of individuals in terms of their interactions with others, and probabilistic sequential models, for the recognition of role sequences underlying the sequence of speakers in conversations. The experiments are performed over different kinds of data (around 90 hours of broadcast data and meetings), and show that the performance depends on how formal the roles are, i.e. on how much they constrain people behavior. Categories and Subject Descriptors: H.3.1 [Content Analysis and Indexing]. General Terms: Experimenta
Sarah Favre, Alfred Dielmann, Alessandro Vinciarel
Added 23 Jul 2010
Updated 23 Jul 2010
Type Conference
Year 2009
Where MM
Authors Sarah Favre, Alfred Dielmann, Alessandro Vinciarelli
Comments (0)
books