ADDITIVE NOISE COMPENSATION IN THE I-VECTOR SPACE FOR SPEAKER RECOGNITION - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

ADDITIVE NOISE COMPENSATION IN THE I-VECTOR SPACE FOR SPEAKER RECOGNITION

Résumé

State-of-the-art speaker recognition systems performance degrades considerably in noisy environments even though they achieve very good results in clean conditions. In order to deal with this strong limitation, we aim in this work to remove the noisy part of an i-vector directly in the i-vector space. Our approach offers the advantage to operate only at the i-vector extraction level, letting the other steps of the system unchanged. A maximum a posteriori (MAP) procedure is applied in order to obtain clean version of the noisy i-vectors taking advantage of prior knowledge about clean i-vectors distribution. To perform this MAP estimation, Gaussian assumptions over clean and noise i-vectors distributions are made. Operating on NIST 2008 data, we show a relative improvement up to 60% compared with baseline system. Our approach also out-performs the "multi-style" backend training technique. The efficiency of the proposed method is obtained at the price of relative high computational cost. We present at the end some ideas to improve this aspect.
Fichier principal
Vignette du fichier
waad_benkheder_icassp2015.pdf (279.25 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02157205 , version 1 (15-06-2019)

Identifiants

  • HAL Id : hal-02157205 , version 1

Citer

Waad Ben Kheder, Driss Matrouf, Jean-François Bonastre, Moez Ajili, Pierre-Michel Bousquet Bousquet. ADDITIVE NOISE COMPENSATION IN THE I-VECTOR SPACE FOR SPEAKER RECOGNITION. ICASSP, 2015, South Brisbane, Australia. ⟨hal-02157205⟩

Collections

UNIV-AVIGNON LIA
32 Consultations
111 Téléchargements

Partager

Gmail Facebook X LinkedIn More