Abstract—Recurrent spiking neurons with lateral inhibition
connection play a vital role in human’s brain functional abilities.
In this paper, we propose a novel noise reduction method that is
based on neuron rate coding and bio-inspired spiking neural
network architecture. The excitatory-inhibitory topology in the
network acts as the temporal characteristic synchrony and
coincidence detector that removes uncorrelated noisy spikes. A
LIF source encoder is introduced along with the network. The
network uses generated binary Short-Time Fourier Transform
(STFT) masks according to the rate of processed spike train,
which is used to reconstruct the denoised speech signal. The
technique is evaluated on noisy speech samples with 5 types of
real-world additive noise with different noise strength.
Index Terms—Spiking neural network, speech enhancement, noise reduction, lateral inhibition.
Yannan Xing, Weijie Ke, Gaetano Di Caterina, and John Soraghan are with the Deep Learning and Neuromorphic Lab, Centre for Image and Signal Processing, Electronics and Electrical Engineering Department University of Strathclyde, Glasgow, UK (e-mail: yannan.xing@ strath.ac.uk).
Cite: Yannan Xing, Weijie Ke, Gaetano Di Caterina, and John Soraghan, "Noise Reduction Using Neural Lateral Inhibition for Speech Enhancement," International Journal of Machine Learning and Computing vol. 11, no. 5, pp. 357-361, 2021.Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).