Duration mismatch compensation using four-covariance model and deep neural network for speaker verification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Duration mismatch compensation using four-covariance model and deep neural network for speaker verification

Résumé

Duration mismatch between enrollment and test utterances still remains a major concern for reliability of real-life speaker recognition applications. Two approaches are proposed here to deal with this case when using the i-vector representation. The first one is an adaptation of Gaussian Probabilistic Linear Discriminant Analysis (PLDA) modeling, which can be extended to the case of any shift between i-vectors drawn from two distinct distributions. The second one attempts to map i-vectors of truncated segments of an utterance to the i-vector of the full segment, by the use of deep neural networks (DNN). Our results show that both new approaches outperform the standard PLDA by about 10 % relative, noting that these back-end methods could complement those quantifying the i-vector uncertainty during its extraction process, in the case of duration gap.
Fichier principal
Vignette du fichier
LIA_pmb_interSp2017.pdf (578.05 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02159806 , version 1 (19-06-2019)

Identifiants

Citer

Pierre-Michel Bousquet Bousquet, Mickael Rouvier. Duration mismatch compensation using four-covariance model and deep neural network for speaker verification. InterSpeech, 2017, Stockholm, Sweden. ⟨10.21437/Interspeech.2017-93⟩. ⟨hal-02159806⟩

Collections

UNIV-AVIGNON LIA
23 Consultations
78 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More