A Two-Stage U-Net for High-Fidelity Denoising of Historical Recordings

TL;DR

This paper introduces a two-stage U-Net deep neural network for high-fidelity denoising of historical audio recordings, effectively removing various noise types and outperforming previous methods in quality.

Contribution

A novel two-stage U-Net architecture designed specifically for high-fidelity denoising of historical recordings using realistic training data.

Findings

Outperforms previous denoising methods in objective metrics

Significantly improves subjective listening test scores

Effectively removes hiss, clicks, and other disturbances

Abstract

Enhancing the sound quality of historical music recordings is a long-standing problem. This paper presents a novel denoising method based on a fully-convolutional deep neural network. A two-stage U-Net model architecture is designed to model and suppress the degradations with high fidelity. The method processes the time-frequency representation of audio, and is trained using realistic noisy data to jointly remove hiss, clicks, thumps, and other common additive disturbances from old analog discs. The proposed model outperforms previous methods in both objective and subjective metrics. The results of a formal blind listening test show that real gramophone recordings denoised with this method have significantly better quality than the baseline methods. This study shows the importance of realistic training data and the power of deep learning in audio restoration.