Topic Segmentation in a Media Watch System

Authors:
Rui Amaral;Isabel Trancoso
Affiliations:
Instituto Superior Técnico, and Instituto Politécnico de Setúbal, and L2F - Spoken Language Systems Lab, INESC-ID,;Instituto Superior Técnico, and L2F - Spoken Language Systems Lab, INESC-ID,
Venue:
PROPOR '08 Proceedings of the 8th international conference on Computational Processing of the Portuguese Language
Year:
2008

Citing 1
Cited 0

The Rules Behind Roles: Identifying Speaker Role in Radio Broadcasts

Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes our on-going work on the topic segmentation module of a media watch system. The current version explores not only the typical structure of a broadcast news show, but also its contents, which are automatically produced by the speech recognition module, and the topic indexation module. The performance of the automatic topic segmentation module was compared with the manual segmentation done by a professional media watch company, yielding quite satisfactory results.