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...
Main Authors: | Abdennour Alimohad, Ahmed Bouridane, Abderrezak Guessoum |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2014-10-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/14/10/19007 |
Similar Items
-
Improving Speaker Recognition by Biometric Voice Deconstruction
by: Luis Miguel eMazaira-Fernández, et al.
Published: (2015-09-01) -
Recognition of Aircraft Engine Sound Based on GMM-UBM Model
by: Yuan Shuai, et al.
Published: (2017-01-01) -
ROBUST HYBRID FEATURES BASED TEXT INDEPENDENT SPEAKER IDENTIFICATION SYSTEM OVER NOISY ADDITIVE CHANNEL
by: Ali Muayad Jalil, et al.
Published: (2020-07-01) -
Automatic text-independent speaker verification using convolutional deep belief network
by: I.A. Rakhmanenko, et al.
Published: (2020-08-01) -
Real Time Recognition Of Speakers From Internet Audio Stream
by: Weychan Radoslaw, et al.
Published: (2015-09-01)