Speaker Diarization With Unsupervised Training Framework

Abstract : This paper investigates single and cross-show diarization based on an unsupervised i-vector framework, on French TV and Radio corpora. This framework uses speaker clustering as a way to automatically select data from unlabeled corpora to train i-vector PLDA models. Performances between supervised and unsupervised models are compared. The experimental results on two distinct test corpora (one TV, one Radio) show that unsupervised models perform as good as supervised models for both tasks. Such results indicate that performing an effective cross-show diarization on new language or new domain data in the future should not depend on the availability of manually annotated data.
Type de document :
Communication dans un congrès
41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), Mar 2016, Shanghai, China. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.5, 2016, 〈10.1109/ICASSP.2016.7472741〉
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01433167
Contributeur : Sylvain Meignier <>
Soumis le : mercredi 22 mars 2017 - 00:18:11
Dernière modification le : jeudi 6 avril 2017 - 10:15:01
Document(s) archivé(s) le : vendredi 23 juin 2017 - 12:34:26

Fichier

speaker-diarization-unsupervis...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Gaël Le Lan, Sylvain Meignier, Delphine Charlet, Paul Deléglise. Speaker Diarization With Unsupervised Training Framework. 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), Mar 2016, Shanghai, China. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.5, 2016, 〈10.1109/ICASSP.2016.7472741〉. 〈hal-01433167〉

Partager

Métriques

Consultations de la notice

148

Téléchargements de fichiers

461