Automatic speaker verification using Nearest Neighbor Normalization (3N) on an iPad tablet - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Automatic speaker verification using Nearest Neighbor Normalization (3N) on an iPad tablet

Résumé

This paper describes the development, implementation and validation of an automatic speaker recognition system on an iPad tablet. A score normalization approach, referred as Nearest Neighbor Normalization (3N), is applied in order to improve the baseline speaker verification system. The system is evaluated on the MOBIO corpus and results show an absolute improvement of the HTER by more than 4% when the score normalization is performed. A human-centered interface is implemented for the speaker recognition system and a survey is collected from 28 users in order to evaluate the application. The results showed that the users, familiar with touchscreen interface, found the application easy to learn and use
Fichier principal
Vignette du fichier
khemiri-biosig-2014.pdf (158.38 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01262413 , version 1 (26-01-2016)

Identifiants

  • HAL Id : hal-01262413 , version 1

Citer

Houssemeddine Khemiri, Alexander Usoltsev, Marie Christine Legout, Dijana Petrovska-Delacrétaz, Gérard Chollet. Automatic speaker verification using Nearest Neighbor Normalization (3N) on an iPad tablet. BIOSIG 2014 : International Conference of the Biometrics Special Interest Group , Sep 2014, Darmstadt, Germany. pp.243 - 250. ⟨hal-01262413⟩
99 Consultations
47 Téléchargements

Partager

Gmail Facebook X LinkedIn More