Efficient Invariant Features for Sensor Variability Compensation in Speaker Recognition

Alimohad, Abdennour, Bouridane, Ahmed and Guessoum, Abderrezak (2014) Efficient Invariant Features for Sensor Variability Compensation in Speaker Recognition. Sensors, 14 (10). pp. 19007-19022. ISSN 1424-8220

[img]
Preview
PDF
sensors-14-19007-v2.pdf - Published Version

Download (645kB) | Preview
Official URL: http://dx.doi.org/10.3390/s141019007

Abstract

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 systems. Our experiments show: (1) the effectiveness of these features in match cases; (2) the benefit of combining these features with the mel frequency cepstral coefficients to exploit their discrimination power under uncontrolled conditions (mismatch cases). Consequently, the proposed invariant features result in a performance improvement as demonstrated by a reduction in the equal error rate and the minimum decision cost function compared to the GMM-UBM speaker recognition systems based on MFCC features.

Item Type: Article
Uncontrolled Keywords: speaker recognition, invariant features, MFCCs, GMM-UBM, sensor variability, DET curve
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer Science and Digital Technologies
Depositing User: Becky Skoyles
Date Deposited: 21 Oct 2014 07:35
Last Modified: 11 May 2017 09:10
URI: http://nrl.northumbria.ac.uk/id/eprint/17754

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics


Policies: NRL Policies | NRL University Deposit Policy | NRL Deposit Licence