Topic Segmentation of TV-streams by mathematical morphology and vectorization

Vincent Claveau 1 Sébastien Lefèvre 2
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : A fine-grained segmentation of Radio or TV broadcasts is an essential step for most multimedia processings. Applying seg- mentation algorithms to the speech transcripts seems straight- forward. Yet, most of these algorithms are not suited when dealing with short segments or noisy data. In this paper, we propose a new segmentation technique inspired from the im- age segmentation field and relying on a new way to compute similarities between candidate segments. This new topic seg- mentation technique is evaluated on two corpora of French TV broadcasts on which it largely outperforms other existing ap- proaches from the state-of-the-art.
Type de document :
Communication dans un congrès
InterSpeech, 2011, Italy. 2011
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00643905
Contributeur : Vincent Claveau <>
Soumis le : mercredi 23 novembre 2011 - 11:23:08
Dernière modification le : vendredi 13 janvier 2017 - 14:21:09

Identifiants

  • HAL Id : hal-00643905, version 1

Collections

Citation

Vincent Claveau, Sébastien Lefèvre. Topic Segmentation of TV-streams by mathematical morphology and vectorization. InterSpeech, 2011, Italy. 2011. <hal-00643905>

Partager

Métriques

Consultations de la notice

232