Constrained discriminative speaker verification specific to normalized i-vectors - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2016

Constrained discriminative speaker verification specific to normalized i-vectors

Résumé

This paper focuses on discriminative trainings (DT) applied to i-vectors after Gaussian probabilistic linear discriminant analysis (PLDA). If DT has been successfully used with non-normalized vectors, this technique struggles to improve speaker detection when i-vectors have been first normalized, whereas the latter option has proven to achieve best performance in speaker verification. We propose an additional normalization procedure which limits the amount of coefficient to discriminatively train, with a minimal loss of accuracy. Adaptations of logistic regression based-DT to this new configuration are proposed, then we introduce a discriminative classifier for speaker verification which is a novelty in the field.
Fichier principal
Vignette du fichier
Odyssey_2016_paper_3.pdf (216.86 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02159804 , version 1 (19-06-2019)

Identifiants

  • HAL Id : hal-02159804 , version 1

Citer

Pierre-Michel Bousquet Bousquet, Jean-François Bonastre. Constrained discriminative speaker verification specific to normalized i-vectors. Odyssey: The Speaker and Language Recognition Workshop, 2016, Bilbao, Spain. ⟨hal-02159804⟩

Collections

UNIV-AVIGNON LIA
20 Consultations
78 Téléchargements

Partager

Gmail Facebook X LinkedIn More