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

arXiv: https://arxiv.org/abs/2508.03448 · HTML: https://mlsanity.com/paper/2508.03448/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 68 references that are in the map.
- First posted on arXiv 5 Aug 2025.

## Builds on (most cited first, 30 of 44)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [Fast Timing-Conditioned Latent Audio Diffusion](https://mlsanity.com/paper/2402.04825/) (2024)
- [Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound](https://mlsanity.com/paper/2502.05139/) (2025)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [Mustango: Toward Controllable Text-to-Music Generation](https://mlsanity.com/paper/2311.08355/) (2023)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models](https://mlsanity.com/paper/2304.00830/) (2023)
- [Phase-aware Speech Enhancement with Deep Complex U-Net](https://mlsanity.com/paper/1903.03107/) (2019)
- [Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation](https://mlsanity.com/paper/2007.13975/) (2020)
- [TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization](https://mlsanity.com/paper/2412.21037/) (2024)
- [Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion](https://mlsanity.com/paper/2402.10009/) (2024)
- [VoiceFixer: Toward General Speech Restoration with Neural Vocoder](https://mlsanity.com/paper/2109.13731/) (2021)
- [A Wavenet for Speech Denoising](https://mlsanity.com/paper/1706.07162/) (2017)
- [MusicMagus: Zero-Shot Text-to-Music Editing via Diffusion Models](https://mlsanity.com/paper/2402.06178/) (2024)
- [Diffusion Models for Audio Restoration](https://mlsanity.com/paper/2402.09821/) (2024)
- [Automatic multitrack mixing with a differentiable mixing console of neural audio effects](https://mlsanity.com/paper/2010.10291/) (2020)
- [MaskSR: Masked Language Model for Full-band Speech Restoration](https://mlsanity.com/paper/2406.02092/) (2024)
- [Blind Audio Bandwidth Extension: A Diffusion-Based Zero-Shot Approach](https://mlsanity.com/paper/2306.01433/) (2023)
- [FlowSep: Language-Queried Sound Separation with Rectified Flow Matching](https://mlsanity.com/paper/2409.07614/) (2024)
- [FLUX that Plays Music](https://mlsanity.com/paper/2409.00587/) (2024)
- [Efficient neural networks for real-time modeling of analog dynamic range compression](https://mlsanity.com/paper/2102.06200/) (2021)
- [JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata](https://mlsanity.com/paper/2502.07461/) (2025)
- [BEHM-GAN: Bandwidth Extension of Historical Music using Generative Adversarial Networks](https://mlsanity.com/paper/2204.06478/) (2022)
- [Diffusion-Based Audio Inpainting](https://mlsanity.com/paper/2305.15266/) (2023)

## Built on by (most cited first, 6 of 6)

- [ALARM: Audio-Language Alignment for Reasoning Models](https://mlsanity.com/paper/2603.09556/) (2026)
- [Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings](https://mlsanity.com/paper/2607.03806/) (2026)
- [Single-step Controllable Music Bandwidth Extension With Flow Matching](https://mlsanity.com/paper/2601.14356/) (2026)
- [Multi-Stage Music Source Restoration with BandSplit-RoFormer Separation and HiFi++ GAN](https://mlsanity.com/paper/2603.04032/) (2026)
- [Music Source Restoration with Ensemble Separation and Targeted Reconstruction](https://mlsanity.com/paper/2603.16926/) (2026)
- [HAIM: Human-AI Music Datasets for AI Music Production Tracking Benchmark](https://mlsanity.com/paper/2606.01686/) (2026)

## Abstract (arXiv)

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.