State-of-the-Art Performance in Text-Independent Speaker Verification Through Open-Source Software - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Audio, Speech and Language Processing Année : 2007

State-of-the-Art Performance in Text-Independent Speaker Verification Through Open-Source Software

Résumé

—This paper illustrates an evolution in state-of-the-art speaker verification by highlighting the contribution from newly developed techniques. Starting from a baseline system based on Gaussian mixture models that reached state-of-the-art performances during the NIST'04 SRE, final systems with new intersession compensation techniques show a relative gain of around 50%. This work highlights that a key element in recent improvements is still the classical maximum a posteriori (MAP) adaptation, while the latest compensation methods have a crucial impact on overall performances. Nuisance attribute projection (NAP) and factor analysis (FA) are examined and shown to provide significant improvements. For FA, a new symmetrical scoring (SFA) approach is proposed. We also show further improvement with an original combination between a support vector machine and SFA. This work is undertaken through the open-source ALIZE toolkit.
Fichier non déposé

Dates et versions

hal-01311358 , version 1 (04-05-2016)

Identifiants

Citer

Driss Matrouf, Nicolas Scheffer, Jean-François Bonastre. State-of-the-Art Performance in Text-Independent Speaker Verification Through Open-Source Software. IEEE Transactions on Audio, Speech and Language Processing, 2007, ⟨10.1109/TASL.2007.902877⟩. ⟨hal-01311358⟩

Collections

UNIV-AVIGNON LIA
46 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More