First investigations on self trained speaker diarization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

First investigations on self trained speaker diarization

Résumé

This paper investigates self trained cross-show speaker diarization applied to collections of French TV archives, based on an i-vector/PLDA framework. The parameters used for i-vectors extraction and PLDA scoring are trained in a unsupervised way, using the data of the collection itself. Performances are compared, using combinations of target data and external data for training. The experimental results on two distinct target cor- pora show that using data from the corpora themselves to perform unsupervised iterative training and domain adaptation of PLDA parameters can improve an existing system, trained on external annotated data. Such results indicate that perform- ing speaker indexation on small collections of unlabeled audio archives should only rely on the availability of a sufficient external corpus, which can be specifically adapted to every target collection. We show that a minimum collection size is required to exclude the use of such an external bootstrap.
Fichier principal
Vignette du fichier
50.pdf (235.99 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01433173 , version 1 (24-03-2017)

Identifiants

  • HAL Id : hal-01433173 , version 1

Citer

Gaël Le Lan, Sylvain Meignier, Delphine Charlet, Anthony Larcher. First investigations on self trained speaker diarization. Speaker and Language Recognition Workshop (Speaker Odyssey), Jun 2016, Bilbao, Spain. pp.152-157. ⟨hal-01433173⟩
256 Consultations
102 Téléchargements

Partager

Gmail Facebook X LinkedIn More