Automatic role recognition in multiparty conversations: An approach based on turn organization, prosody, and conditional random fields

Salamin, H. and Vinciarelli, A. (2012) Automatic role recognition in multiparty conversations: An approach based on turn organization, prosody, and conditional random fields. IEEE Transactions on Multimedia, 14(2), pp. 338-345. (doi:10.1109/TMM.2011.2173927)

Full text not currently available from Enlighten.

Publisher's URL: http://dx.doi.org/10.1109/TMM.2011.2173927

Abstract

Roles are a key aspect of social interactions, as they contribute to the overall predictability of social behavior (a necessary requirement to deal effectively with the people around us), and they result in stable, possibly machine-detectable behavioral patterns (a key condition for the application of machine intelligence technologies). This paper proposes an approach for the automatic recognition of roles in conversational broadcast data, in particular, news and talk shows. The approach makes use of behavioral evidence extracted from speaker turns and applies conditional random fields to infer the roles played by different individuals. The experiments are performed over a large amount of broadcast material (around 50 h), and the results show an accuracy higher than 85%.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Salamin, Mr Hugues and Vinciarelli, Professor Alessandro
Authors: Salamin, H., and Vinciarelli, A.
College/School:College of Science and Engineering > School of Computing Science
Journal Name:IEEE Transactions on Multimedia
ISSN:1520-9210
ISSN (Online):1941-0077
Published Online:27 October 2011

University Staff: Request a correction | Enlighten Editors: Update this record