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

Eloi Moliner*, Vesa Välimäki

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

13 Citations (Scopus)
76 Downloads (Pure)

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.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherIEEE
Pages841-845
Number of pages5
ISBN (Electronic)978-1-6654-0540-9
DOIs
Publication statusPublished - 2022
MoE publication typeA4 Conference publication
EventIEEE International Conference on Acoustics, Speech, and Signal Processing - Singapore, Singapore
Duration: 23 May 202227 May 2022

Publication series

Name Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
ISSN (Electronic)2379-190X

Conference

ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated titleICASSP
Country/TerritorySingapore
CitySingapore
Period23/05/202227/05/2022

Keywords

  • Audio systems
  • deep learning
  • music

Fingerprint

Dive into the research topics of 'A Two-Stage U-Net for High-Fidelity Denoising of Historical Recordings'. Together they form a unique fingerprint.

Cite this