PLDA Modeling in I-Vector and Supervector Space for Speaker Verification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

PLDA Modeling in I-Vector and Supervector Space for Speaker Verification

Résumé

In this paper, we advocate the use of uncompressed form of i-vector. We employ the probabilistic linear discriminant analysis (PLDA) to handle speaker and session variability for speaker verification task. An i-vector is a low-dimensional vector containing both speaker and channel information acquired from a speech segment. When PLDA is used on i-vector, dimension reduction is performed twice-first in the i-vector extraction process and second in the PLDA model. Keeping the full dimensionality of i-vector in the supervector space for PLDA modeling and scoring would avoid unnecessary loss of information. The drawback of using PLDA on uncompressed i-vector is the inversion of large matrices, which we show can be solved rather efficiently by portioning large matrix into smaller blocks. We also introduce the Gaussianized rank-norm, as an alternative to whitening, for feature normalization prior to PLDA modeling.
Fichier principal
Vignette du fichier
Jiang12_versionFinale.pdf (226.81 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01927743 , version 1 (20-11-2018)

Identifiants

  • HAL Id : hal-01927743 , version 1

Citer

Ye Jiang, Kong Aik Lee, Zhenmin Tang, Bin Ma, Anthony Larcher, et al.. PLDA Modeling in I-Vector and Supervector Space for Speaker Verification. Annual Conference of the International Speech Communication Association (Interspeech), Sep 2012, Portland, United States. ⟨hal-01927743⟩
96 Consultations
451 Téléchargements

Partager

Gmail Facebook X LinkedIn More