A Two-Stage U-Net for High-Fidelity Denoising of Historical Recordings
Loading...
Access rights
openAccess
URL
Journal Title
Journal ISSN
Volume Title
A4 Artikkeli konferenssijulkaisussa
This publication is imported from Aalto University research portal.
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
View publication in the Research portal (opens in new window)
View/Open full text file from the Research portal (opens in new window)
Other link related to publication (opens in new window)
Authors
Date
2022
Major/Subject
Mcode
Degree programme
Language
en
Pages
5
841-845
841-845
Series
2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
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.Description
Funding Information: This research is part of the activities of the Nordic Sound and Music Computing Network-NordicSMC (NordForsk project no. 86892). Publisher Copyright: © 2022 IEEE
Keywords
Audio systems, deep learning, music
Other note
Citation
Moliner, E & Välimäki, V 2022, A Two-Stage U-Net for High-Fidelity Denoising of Historical Recordings . in 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings . Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, pp. 841-845, IEEE International Conference on Acoustics, Speech, and Signal Processing, Singapore, Singapore, 23/05/2022 . https://doi.org/10.1109/ICASSP43922.2022.9746977