Automatic topic identification in multimedia broadcast data

Steffen Werner, Uri Iurgel, Andreas Kosmala, Gerhard Rigoll

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

Abstract

This paper presents a system that automatically scans multimedia data like TV or radio broadcasts for the presence of specific topics and, whenever topics of users' interests are detected, alerts the related user. Our current work on the three main modules of the system is shown. (1) The speech recognition system (with 18.7 % WER) is already among the most advanced German broadcast speech recognition systems. (2) The innovative topic identification approach, which is especially designed to work on the output of a speech recognizer, is compared to a standard text based approach. (3) The topic segmentation module has a good performance detecting not only scene cuts or speaker turns, but also real topic boundaries.

Original languageEnglish
Title of host publicationProceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages41-44
Number of pages4
ISBN (Electronic)0780373049
DOIs
StatePublished - 2002
Event2002 IEEE International Conference on Multimedia and Expo, ICME 2002 - Lausanne, Switzerland
Duration: 26 Aug 200229 Aug 2002

Publication series

NameProceedings - 2002 IEEE International Conference on Multimedia and Expo, ICME 2002
Volume1

Conference

Conference2002 IEEE International Conference on Multimedia and Expo, ICME 2002
Country/TerritorySwitzerland
CityLausanne
Period26/08/0229/08/02

Fingerprint

Dive into the research topics of 'Automatic topic identification in multimedia broadcast data'. Together they form a unique fingerprint.

Cite this