SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Melechovsky, Jan, Mehrish, Ambuj, Roy, Abhinaba, Herremans, Dorien
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911645283909632
author Melechovsky, Jan
Mehrish, Ambuj
Roy, Abhinaba
Herremans, Dorien
author_facet Melechovsky, Jan
Mehrish, Ambuj
Roy, Abhinaba
Herremans, Dorien
contents Music recordings often suffer from audio quality issues such as excessive reverberation, distortion, clipping, tonal imbalances, and a narrowed stereo image, especially when created in non-professional settings without specialized equipment or expertise. These problems are typically corrected using separate specialized tools and manual adjustments. In this paper, we introduce SonicMaster, the first unified generative model for music restoration and mastering that addresses a broad spectrum of audio artifacts with text-based control. SonicMaster is conditioned on natural language instructions to apply targeted enhancements, or can operate in an automatic mode for general restoration. To train this model, we construct the SonicMaster dataset, a large dataset of paired degraded and high-quality tracks by simulating common degradation types with nineteen degradation functions belonging to five enhancements groups: equalization, dynamics, reverb, amplitude, and stereo. Our approach leverages a flow-matching generative training paradigm to learn an audio transformation that maps degraded inputs to their cleaned, mastered versions guided by text prompts. Objective audio quality metrics demonstrate that SonicMaster significantly improves sound quality across all artifact categories. Furthermore, subjective listening tests confirm that listeners prefer SonicMaster's enhanced outputs over other baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2508_03448
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
Melechovsky, Jan
Mehrish, Ambuj
Roy, Abhinaba
Herremans, Dorien
Sound
Artificial Intelligence
Multimedia
Audio and Speech Processing
68T07, 94A12, 68U10
I.2.10; H.5.5; J.5
Music recordings often suffer from audio quality issues such as excessive reverberation, distortion, clipping, tonal imbalances, and a narrowed stereo image, especially when created in non-professional settings without specialized equipment or expertise. These problems are typically corrected using separate specialized tools and manual adjustments. In this paper, we introduce SonicMaster, the first unified generative model for music restoration and mastering that addresses a broad spectrum of audio artifacts with text-based control. SonicMaster is conditioned on natural language instructions to apply targeted enhancements, or can operate in an automatic mode for general restoration. To train this model, we construct the SonicMaster dataset, a large dataset of paired degraded and high-quality tracks by simulating common degradation types with nineteen degradation functions belonging to five enhancements groups: equalization, dynamics, reverb, amplitude, and stereo. Our approach leverages a flow-matching generative training paradigm to learn an audio transformation that maps degraded inputs to their cleaned, mastered versions guided by text prompts. Objective audio quality metrics demonstrate that SonicMaster significantly improves sound quality across all artifact categories. Furthermore, subjective listening tests confirm that listeners prefer SonicMaster's enhanced outputs over other baselines.
title SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
topic Sound
Artificial Intelligence
Multimedia
Audio and Speech Processing
68T07, 94A12, 68U10
I.2.10; H.5.5; J.5
url https://arxiv.org/abs/2508.03448