Edinburgh Research Explorer

Multi-stream segmentation of meetings

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publication2004 IEEE 6th Workshop on Multimedia Signal Processing
Subtitle of host publicationMMSP 2004
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages167-170
ISBN (Print)0-7803-8578-0
DOIs
Publication statusPublished - 2004
EventIEEE 6th Workshop on Multimedia Signal Processing (MMSP 2004) - Siena, Italy
Duration: 29 Sep 20041 Oct 2004

Workshop

WorkshopIEEE 6th Workshop on Multimedia Signal Processing (MMSP 2004)
CountryItaly
CitySiena
Period29/09/041/10/04

Abstract

This paper investigates the automatic segmentation of meetings into a sequence of group actions or phases. Our work is based on a corpus of multiparty meetings collected in a meeting room instrumented with video cameras, lapel microphones and a microphone array. We have extracted a set of feature streams, in this case extracted from the audio data, based on speaker turns, prosody and a transcript of what was spoken. We have related these signals to the higher level semantic categories via a multistream statistical model based on dynamic Bayesian networks (DBNs). We report on a set of experiments in which different DBN architectures are compared, together with the different feature streams. The resultant system has an action error rate of 9%.

Event

IEEE 6th Workshop on Multimedia Signal Processing (MMSP 2004)

29/09/041/10/04

Siena, Italy

Event: Workshop

Download statistics

No data available

ID: 27411502