Comparative Analysis Of Discriminative Deep Learning-Based Noise Reduction Methods In Low SNR Scenarios

TL;DR

This paper provides a comprehensive comparison of deep learning-based noise reduction methods in low SNR scenarios, analyzing factors like training data, loss functions, and model capacities to guide better technique selection.

Contribution

It offers a detailed comparative analysis of various deep learning noise reduction techniques specifically in low SNR conditions, highlighting their strengths and weaknesses.

Findings

Different training data significantly affect noise reduction performance.

Loss functions influence speech quality and noise suppression balance.

Model capacity impacts effectiveness and computational efficiency.

Abstract

In this study, we conduct a comparative analysis of deep learning-based noise reduction methods in low signal-to-noise ratio (SNR) scenarios. Our investigation primarily focuses on five key aspects: The impact of training data, the influence of various loss functions, the effectiveness of direct and indirect speech estimation techniques, the efficacy of masking, mapping, and deep filtering methodologies, and the exploration of different model capacities on noise reduction performance and speech quality. Through comprehensive experimentation, we provide insights into the strengths, weaknesses, and applicability of these methods in low SNR environments. The findings derived from our analysis are intended to assist both researchers and practitioners in selecting better techniques tailored to their specific applications within the domain of low SNR noise reduction.