PHONETICALLY-CONSTRAINED PLDA MODELING FOR TEXT-DEPENDENT SPEAKER VERIFICATION WITH MULTIPLE SHORT UTTERANCES

Abstract : The importance of phonetic variability for short duration speaker verification is widely acknowledged. This paper assesses the performance of Probabilistic Linear Discriminant Analysis (PLDA) and i-vector normalization for a text-dependent verification task. We show that using a class definition based on both speaker and pho-netic content significantly improves the performance of a state-of-the-art system. We also compare four models for computing the verification scores using multiple enrollment utterances and show that using PLDA intrinsic scoring obtains the best performance in this context. This study suggests that such scoring regime remains to be optimized.
Type de document :
Communication dans un congrès
IEEE International Conference on Acoustic Speech and Signal Processing, May 2013, Vancouver, Canada
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01927589
Contributeur : Anthony Larcher <>
Soumis le : lundi 19 novembre 2018 - 23:57:11
Dernière modification le : jeudi 22 novembre 2018 - 01:10:00
Document(s) archivé(s) le : mercredi 20 février 2019 - 16:11:09

Fichier

Icassp13_TD-IV_v0.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01927589, version 1

Collections

Citation

Anthony Larcher, Kong Aik Lee, Bin Ma, Haizhou Li. PHONETICALLY-CONSTRAINED PLDA MODELING FOR TEXT-DEPENDENT SPEAKER VERIFICATION WITH MULTIPLE SHORT UTTERANCES. IEEE International Conference on Acoustic Speech and Signal Processing, May 2013, Vancouver, Canada. 〈hal-01927589〉

Partager

Métriques

Consultations de la notice

13

Téléchargements de fichiers

19