Title
Automatic detection of interaction groups
Abstract
This paper addresses the problem of detecting interaction groups in an intelligent environment. To understand human activity, we need to identify human actors and their interpersonal links. An interaction group can be seen as basic entity, within which individuals collaborate in order to achieve a common goal. In this regard, the dynamic change of interaction group configuration, i.e. the split and merge of interaction groups, can be seen as indicator of new activities. Our approach takes speech activity detection of individuals forming interaction groups as input. A classical HMM-based approach learning different HMM for the different group configurations did not produce promising results. We propose an approach for detecting interaction group configurations based on the assumption that conversational turn taking is synchronized inside groups. The proposed detector is based on one HMM constructed upon conversational hypotheses. The approach shows good results and thus confirms our conversational hypotheses.
Year
DOI
Venue
2005
10.1145/1088463.1088473
Int. Conf. on Multimodal Interfaces
Keywords
Field
DocType
human actor,automatic detection,human activity,conversational turn taking,ubiquitous computing,intelligent environment,classical hmm-based approach,clustering interaction groups,interaction group,new activity,conversational hypothesis,different hmm,interaction group configuration,conversational analysis,different group configuration,hidden markov model,speech detection,speech activity detection
Intelligent environment,Interpersonal communication,Turn-taking,Computer science,Voice activity detection,Human–computer interaction,Artificial intelligence,Ubiquitous computing,Hidden Markov model,Merge (version control),Detector
Conference
ISBN
Citations 
PageRank 
1-59593-028-0
47
3.32
References 
Authors
4
3
Name
Order
Citations
PageRank
Oliver Brdiczka1107657.49
Jérôme Maisonnasse219210.67
Patrick Reignier337945.38