Development of an adaptive line enhancer using nonlinear neural networks

Authors:
Roshahliza M. Ramli;Ali O. Abid Noor;Salina Abdul Samad
Affiliations:
Department of Electrical, Electronics and System Engineering, Universiti Kebangsaan Malaysia, Selangor Darul Ehsan, Malaysia;Department of Electrical, Electronics and System Engineering, Universiti Kebangsaan Malaysia, Selangor Darul Ehsan, Malaysia;Department of Electrical, Electronics and System Engineering, Universiti Kebangsaan Malaysia, Selangor Darul Ehsan, Malaysia
Venue:
EHAC'12/ISPRA/NANOTECHNOLOGY'12 Proceedings of the 11th WSEAS international conference on Electronics, Hardware, Wireless and Optical Communications, and proceedings of the 11th WSEAS international conference on Signal Processing, Robotics and Automation, and proceedings of the 4th WSEAS international conference on Nanotechnology
Year:
2012

Citing 7
Cited 0

Separation of real-world signals

Signal Processing - Special issue on acoustic echo and noise control
An Introduction to Neural Networks

An Introduction to Neural Networks
Neural methods for antenna array signal processing: a review

Signal Processing
Microphone arrays for hearing aids: an overview

Speech Communication - Special issue on speech processing for hearing aids
Adaptive Filters

Adaptive Filters
Comparison of MLP neural network and Kalman filter for localization in wireless sensor networks

PDCS '07 Proceedings of the 19th IASTED International Conference on Parallel and Distributed Computing and Systems
A Fast Affine Projection Algorithm Based on Matching Pursuit in Adaptive Noise Cancellation for Speech Enhancement

ISMS '10 Proceedings of the 2010 International Conference on Intelligent Systems, Modelling and Simulation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a special adaptive line enhancer (ALE) structure is developed and tested. The ALE is based on a combination of adaptive filtering and an adaptive nonlinear neural network (ADNN). The main objective of the work is to reduce the background noise from the signal of interest. The proposed structure consists of a three-layer feed forward network with partially connected layers to achieve fast processing. The feedback error is used to train the ADNN. This system is simulated with different levels of interference signals. A comparison analysis of the proposed structure with a classical adaptive least mean square (LMS) line enhancer is presented in this paper. The nonlinear ADNN approach investigated here exhibited noticeable improvements over the traditional NLMS approach.