Improving Speaker Recognition in Environmental Noise With Adaptive Filter
Open Access
- 28 November 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 124523-124533
Abstract
Speaker recognition is challenging in real-world environments. Typically, studies approach noises only in an additive manner. However, real environments commonly present reverberating conditions that worsen speech processing. When not considering reverberation in the system modeling, the system may not be robust when applied to real-world conditions. In this work, we use a slight different approach to simulate reverberation, considering randomized conditions of the environment. With this approach, each VoxCeleb1 test sample is corrupted by randomly generated conditions, with diversified amplitudes of noise and speech.We generate a corrupted dataset, in which the best model EER degraded from 0.93% to 30.13%. To improve this degradation, we propose using Normalized Kernel Least-Mean-Square (NKLMS) adaptive filter. Through the use of NKLMS, we were able to improve the EER from 30.13% to 1.11%. The results indicate that NKLMS has a great potential for speech enhancement to improve speaker recognition.Keywords
Funding Information
- Spanish Agencia Estatal de Investigación
- Project Monitoring and Tracking Systems for the Improvement of Intelligent Mobility and Behavior Analysis (PID2019-108883RB-C21/AEI/10.13039/501100011033)
This publication has 40 references indexed in Scilit:
- A Unified Joint Model to Deal With Nuisance Variabilities in the i-Vector SpaceIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2018
- Theoretical transient analysis of a hearing aid feedback canceller with a saturation type nonlinearity in the direct pathComputers in Biology and Medicine, 2017
- The Speakers in the Wild (SITW) Speaker Recognition Database2016
- Adaptive FiltersAcademic Press Library in Signal Processing, 2014
- Stochastic Behavior Analysis of the Gaussian Kernel Least-Mean-Square AlgorithmIEEE Transactions on Signal Processing, 2012
- Independent Component Analysis by Entropy Bound MinimizationIEEE Transactions on Signal Processing, 2010
- A new modeling algorithm - Normalized Kernel Least Mean Square2009
- Babble Noise: Modeling, Analysis, and ApplicationsIEEE Transactions on Audio, Speech, and Language Processing, 2009
- The Kernel Least-Mean-Square AlgorithmIEEE Transactions on Signal Processing, 2008
- Adaptive noise cancelling: Principles and applicationsProceedings of the IEEE, 1975