Variance-Spectra based Normalization for I-vector Standard and Probabilistic Linear Discriminant Analysis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Variance-Spectra based Normalization for I-vector Standard and Probabilistic Linear Discriminant Analysis

Résumé

I-vector extraction and Probabilistic Linear Discriminant Analysis (PLDA) has become the state-of-the-art configuration for speaker verification. Recently, Gaussian-PLDA has been improved by a preliminary length normalization of i-vectors. This normalization, known to increase the Gaussianity of the i-vector distribution, also improves performance of systems based on standard Linear Discriminant Analysis (LDA) and "two-covariance model" scoring. But this technique follows a standardization of the i-vectors (centering and whitening i-vectors based on the first and second order moments of the development data). We propose in this paper two techniques of normalization based on total, between-and within-speaker variance spectra 1. These "spectral" techniques both normalize the i-vectors length for Gaussianity, but the first adapts the i-vectors representation to a speaker recognition system based on LDA and two-covariance scoring when the second adapts it to a Gaussian-PLDA model. Significant performance improvements are demonstrated on the male and female telephone portion of NIST SRE 2010.
Fichier principal
Vignette du fichier
paperSpectralNormV6.pdf (385.72 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01927751 , version 1 (20-11-2018)

Identifiants

  • HAL Id : hal-01927751 , version 1

Citer

Pierre-Michel Bousquet, Anthony Larcher, Driss Matrouf, Jean-François Bonastre, Oldřich Plchot. Variance-Spectra based Normalization for I-vector Standard and Probabilistic Linear Discriminant Analysis. Speaker Odyssey, Jun 2012, Singapour, Singapore. ⟨hal-01927751⟩

Collections

UNIV-AVIGNON LIA
195 Consultations
143 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More