An active learning method for speaker identity annotation in audio recordings

Abstract : Given that manual annotation of speech is an expensive and long process, we attempt in this paper to assist an anno-tator to perform a speaker diarization. This assistance takes place in an annotation background for a large amount of archives. We propose a method which decreases the intervention number of a human. This method corrects a diarization by taking into account the human interventions. The experiment is done using French broadcast TV shows drawn from ANR-REPERE evaluation campaign. Our method is mainly evaluated in terms of KSR (Keystroke Saving Rate), and we reduce the number of actions needed to correct a speaker diarization output by 6.8% in absolute value.
Type de document :
Communication dans un congrès
1st International Workshop on Multimodal Media Data Analytics (MMDA 2016), Aug 2016, La Haye, Netherlands. Proceedings of the 1st International Workshop on Multimodal Media Data Analytics, 2016, 〈http://mklab.iti.gr/mmda2016/〉
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01451532
Contributeur : Hakim Amokrane <>
Soumis le : jeudi 6 avril 2017 - 09:02:16
Dernière modification le : mardi 19 décembre 2017 - 14:42:03
Document(s) archivé(s) le : vendredi 7 juillet 2017 - 12:21:16

Fichier

paper5.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-01451532, version 1

Collections

Citation

Pierre-Alexandre Broux, David Doukhan, Simon Petitrenaud, Sylvain Meignier, Jean Carrive. An active learning method for speaker identity annotation in audio recordings. 1st International Workshop on Multimodal Media Data Analytics (MMDA 2016), Aug 2016, La Haye, Netherlands. Proceedings of the 1st International Workshop on Multimodal Media Data Analytics, 2016, 〈http://mklab.iti.gr/mmda2016/〉. 〈hal-01451532〉

Partager

Métriques

Consultations de la notice

145

Téléchargements de fichiers

96