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

arXiv: https://arxiv.org/abs/2204.06478 · HTML: https://mlsanity.com/paper/2204.06478/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2022.

## Built on by (most cited first, 13 of 13)

- [Solving Audio Inverse Problems with a Diffusion Model](https://mlsanity.com/paper/2210.15228/) (2022)
- [Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach](https://mlsanity.com/paper/2306.01433/) (2023)
- [AERO: Audio Super Resolution in the Spectral Domain](https://mlsanity.com/paper/2211.12232/) (2022)
- [Audio Super-Resolution with Latent Bridge Models](https://mlsanity.com/paper/2509.17609/) (2025)
- [A Diffusion-Based Generative Equalizer for Music Restoration](https://mlsanity.com/paper/2403.18636/) (2024)
- [A2SB: Audio-to-Audio Schrodinger Bridges](https://mlsanity.com/paper/2501.11311/) (2025)
- [SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering](https://mlsanity.com/paper/2508.03448/) (2025)
- [Learning to Upsample and Upmix Audio in the Latent Domain](https://mlsanity.com/paper/2506.00681/) (2025)
- [UniverSR: Unified and Versatile Audio Super-Resolution via Vocoder-Free Flow Matching](https://mlsanity.com/paper/2510.00771/) (2025)
- [LatentFlowSR: High-Fidelity Audio Super-Resolution via Noise-Robust Latent Flow Matching](https://mlsanity.com/paper/2604.09188/) (2026)
- [SUBARU: A Practical Approach to Power Saving in Hearables Using SUB-Nyquist Audio Resolution Upsampling](https://mlsanity.com/paper/2506.22321/) (2025)
- [Discriminating real and synthetic super-resolved audio samples using embedding-based classifiers](https://mlsanity.com/paper/2601.03443/) (2026)
- [End-to-End Historical Music Restoration in Latent Space](https://mlsanity.com/paper/2610.00607/) (2026)

## Abstract (arXiv)

Audio bandwidth extension aims to expand the spectrum of narrow-band 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 BEHM-GAN, a model based on generative adversarial networks, 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.