Speaker segmentation of interviews using integrated video and audio change detectors

Mathieu Lagrange*, Luis Gustavo Martins, Luis F. Teixeira, George Tzanetakis

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

In this paper, we study the use of audio and visual cues to perform speaker segmentation of audiovisual recordings of formal meetings such as interviews, lectures, or court-room sessions. The sole use of audio cues for such recordings can be ineffective due to low recording quality and high level of background noise. We propose to use additional cues from the video stream by exploiting the relative static locations of speakers among the scene. The experiments show that the combination of those multiple cues helps to identify more robustly the transitions among speakers.
Original languageEnglish
Title of host publicationCBMI'2007 - 2007 International Workshop on Content-Based Multimedia Indexing, Proceedings
Pages219-226
Number of pages8
DOIs
Publication statusPublished - 2007
Externally publishedYes
EventCBMI'2007 - 2007 International Workshop on Content-Based Multimedia Indexing - Bordeaux, France
Duration: 25 Jun 200727 Jun 2007

Publication series

NameCBMI'2007 - 2007 International Workshop on Content-Based Multimedia Indexing, Proceedings

Conference

ConferenceCBMI'2007 - 2007 International Workshop on Content-Based Multimedia Indexing
Country/TerritoryFrance
CityBordeaux
Period25/06/0727/06/07

Fingerprint

Dive into the research topics of 'Speaker segmentation of interviews using integrated video and audio change detectors'. Together they form a unique fingerprint.

Cite this