My SciELO
Services on Demand
Article
Indicators
- Cited by SciELO
Related links
- Similars in SciELO
Share
Revista Cubana de Ciencias Informáticas
On-line version ISSN 2227-1899
Abstract
REYES DIAZ, Flavio J.; ROBLE GUTIERREZ, Alejandro; HERNANDEZ SIERRA, Gabriel and CALVO DE LARA, José Ramón. Wiener filtering to noise reduction for speaker verification.. Rev cuba cienc informat [online]. 2018, vol.12, n.3, pp. 152-162. ISSN 2227-1899.
Audio signals, including voice, are in some way exposed to quality deterioration due to the environmental noise incorporation. These noises existing in the signals, provoke a quality degradation in the speaker acoustic information, bringing with it a decrease of the speaker recognition performance. In this work an analysis of the behavior of some of the main noise reduction methods is performed such as: Wiener Filter and Spectral Subtraction, to pre-procesing the noisy signals. Finally, it is proposed to apply the Wiener filtering to the stage of pre-processing the signals of a speaker recognition system. Then, our proposal are evaluated on telephone session from NIST SRE-08 for different environmental noises types, obtaining an EER improvement of 4,94% and 12,5% for both evaluation conditions.
Keywords : noise; speaker verification; Wiener filter.