Speech Denoising Without Clean Training Data: A Noise2Noise Approach

TL;DR

This paper demonstrates that deep speech denoising networks can be effectively trained solely on noisy speech samples without the need for clean training data, simplifying data collection and improving performance in challenging noise conditions.

Contribution

It introduces a noise2noise training approach for speech denoising that eliminates the need for clean speech targets, outperforming traditional methods in complex noise environments.

Findings

Successful training of speech denoising networks using only noisy data

Superior denoising performance over traditional methods in high noise scenarios

Effective handling of real-world and synthetic noise with Deep Complex U-Net

Abstract

This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio-denoising methods by showing that it is possible to train deep speech denoising networks using only noisy speech samples. Conventional wisdom dictates that in order to achieve good speech denoising performance, there is a requirement for a large quantity of both noisy speech samples and perfectly clean speech samples, resulting in a need for expensive audio recording equipment and extremely controlled soundproof recording studios. These requirements pose significant challenges in data collection, especially in economically disadvantaged regions and for low resource languages. This work shows that speech denoising deep neural networks can be successfully trained utilizing only noisy training audio. Furthermore it is revealed that such training regimes achieve superior denoising performance over conventional training regimes utilizing clean training audio targets, in cases involving complex noise distributions and low Signal-to-Noise ratios (high noise environments). This is demonstrated through experiments studying the efficacy of our proposed approach over both real-world noises and synthetic noises using the 20 layered Deep Complex U-Net architecture.