Deep learning-based filtering of cross-spectral matrices using generative adversarial networks

TL;DR

This paper introduces a deep learning approach using GANs to filter noise and distortions from microphone array data represented as cross-spectral matrices, improving sound processing accuracy.

Contribution

It presents a novel GAN-based method specifically designed for transforming cross-spectral matrices in sound data filtering tasks.

Findings

Effective noise reduction demonstrated in simulated environments

Model successfully performs multiple transformation tasks

Improved sound data quality over traditional filtering methods

Abstract

In this paper, we present a deep-learning method to filter out effects such as ambient noise, reflections, or source directivity from microphone array data represented as cross-spectral matrices. Specifically, we focus on a generative adversarial network (GAN) architecture designed to transform fixed-size cross-spectral matrices. Theses models were trained using sound pressure simulations of varying complexity developed for this purpose. Based on the results from applying these methods in a hyperparameter optimization of an auto-encoding task, we trained the optimized model to perform five distinct transformation tasks derived from different complexities inherent in our sound pressure simulations.