BEHM-GAN: Bandwidth Extension of Historical Music using Generative Adversarial Networks

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Date

2023

Major/Subject

Mcode

Degree programme

Language

en

Pages

14
943-956

Series

IEEE/ACM Transactions on Audio Speech and Language Processing, Volume 31

Abstract

Audio bandwidth extension aims to expand the spectrum of bandlimited audio signals. Although this topic has been broadly studied during recent years, the particular problem of extending the bandwidth of historical music recordings remains an open challenge. This paper proposes a method for the bandwidth extension of historical music using generative adversarial networks (BEHM-GAN) as a practical solution to this problem. The proposed method works with the complex spectrogram representation of audio and, thanks to a dedicated regularization strategy, can effectively extend the bandwidth of out-of-distribution real historical recordings. The BEHM-GAN is designed to be applied as a second step after denoising the recording to suppress any additive disturbances, such as clicks and background noise. We train and evaluate the method using solo piano classical music. The proposed method outperforms the compared baselines in both objective and subjective experiments. The results of a formal blind listening test show that BEHM-GAN significantly increases the perceptual sound quality in early-20th-century gramophone recordings. For several items, there is a substantial improvement in the mean opinion score after enhancing historical recordings with the proposed bandwidth-extension algorithm. This study represents a relevant step toward data-driven music restoration in real-world scenarios.

Description

Lataa julkaisu, kun saatavilla.

Keywords

Audio recording, Bandwidth, convolutional neural networks, Cutoff frequency, Hidden Markov models, machine learning, music, Recording, signal restoration, Speech processing, Task analysis, Training

Other note

Citation

Moliner, E & Valimaki, V 2023, ' BEHM-GAN: Bandwidth Extension of Historical Music using Generative Adversarial Networks ', IEEE/ACM Transactions on Audio Speech and Language Processing, vol. 31, pp. 943-956 . https://doi.org/10.1109/TASLP.2022.3190726