Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

End-to-end speaker segmentation for overlap-aware resegmentation

Abstract : Speaker segmentation consists in partitioning a conversation between one or more speakers into speaker turns. Usually addressed as the late combination of three sub-tasks (voice activity detection, speaker change detection, and overlapped speech detection), we propose to train an end-to-end segmentation model that does it directly. Inspired by the original end-to-end neural speaker diarization approach (EEND), the task is modeled as a multi-label classification problem using permutation-invariant training. The main difference is that our model operates on short audio chunks (5 seconds) but at a much higher temporal resolution (every 16ms). Experiments on multiple speaker diarization datasets conclude that our model can be used with great success on both voice activity detection and overlapped speech detection. Our proposed model can also be used as a post-processing step, to detect and correctly assign overlapped speech regions. Relative diarization error rate improvement over the best considered baseline (VBx) reaches 17% on AMI, 13% on DIHARD 3, and 13% on VoxConverse.
Liste complète des métadonnées

https://hal-univ-lemans.archives-ouvertes.fr/hal-03257524
Contributeur : Antoine Laurent Connectez-vous pour contacter le contributeur
Soumis le : vendredi 11 juin 2021 - 08:48:06
Dernière modification le : mardi 12 octobre 2021 - 16:10:53
Archivage à long terme le : : dimanche 12 septembre 2021 - 18:19:52

Fichier

2104.04045.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-03257524, version 1
  • ARXIV : 2104.04045

Citation

Hervé Bredin, Antoine Laurent. End-to-end speaker segmentation for overlap-aware resegmentation. Interspeech 2021, Aug 2021, Brno, Czech Republic. ⟨hal-03257524⟩

Partager

Métriques

Consultations de la notice

89

Téléchargements de fichiers

43