Informatics Report Series


Report   

EDI-INF-RR-0930


Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Home
Title:Automatic meeting segmentation using dynamic Bayesian networks
Authors: Alfred Dielmann ; Steve Renals
Date:Jan 2007
Publication Title:IEEE Transactions on Multimedia
Publisher:IEEE Signal Processing Society (+ 3 other IEEE societies)
Publication Type:Journal Article Publication Status:Published
Volume No:9 Page Nos:25-36
DOI:10.1109/TMM.2006.886337 ISBN/ISSN:1520-9210
Abstract:
Multiparty meetings are a ubiquitous feature of organizations, and there are considerable economic benefits that would arise from their automatic analysis and structuring. In this paper we are concerned with the segmentation and structuring of meetings (recorded using multiple cameras and microphones) into sequences of group meeting actions such as monologue, discussion and presentation. We outline four families of multimodal features based on speaker turns, lexical transcription, prosody and visual motion that are extracted from the raw audio and video recordings. We relate these low-level features to more complex group behaviours using a multistream modelling framework based on multistream dynamic Bayesian networks. This results in an effective approach to the segmentation problem, resulting in an action error rate of only 12.2%, compared with 43% using an approach based on hidden Markov models. Moreover the multistream dynamic Bayesian network developed here leaves scope for many further improvements and extensions.
Links To Paper
1st Link
Bibtex format
@Article{EDI-INF-RR-0930,
author = { Alfred Dielmann and Steve Renals },
title = {Automatic meeting segmentation using dynamic Bayesian networks},
journal = {IEEE Transactions on Multimedia},
publisher = {IEEE Signal Processing Society (+ 3 other IEEE societies)},
year = 2007,
month = {Jan},
volume = {9},
pages = {25-36},
doi = {10.1109/TMM.2006.886337},
url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumber=4032598&arnumber=4032608&count=20&index=3},
}


Home : Publications : Report 

Please mail <reports@inf.ed.ac.uk> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh