Efficient Invariant Features for Sensor Variability Compensation in Speaker Recognition

Efficient Invariant Features for Sensor Variability Compensation in Speaker Recognition

In this paper, we investigate the use of invariant features for speaker recognition. Owing to their characteristics, these features are introduced to cope with the difficult and challenging problem of sensor variability and the source of performance degradation inherent in speaker recognition system...

Full description

Bibliographic Details
Main Authors: Abdennour Alimohad, Ahmed Bouridane, Abderrezak Guessoum
Format: Article
Language:English
Published: MDPI AG 2014-10-01
Series:Sensors
Subjects:
speaker recognition
invariant features
MFCCs
GMM-UBM
sensor variability
DET curve
Online Access:http://www.mdpi.com/1424-8220/14/10/19007

Similar Items

Similar Items