# VRDMG: Vocal Restoration via Diffusion Posterior Sampling with Multiple Guidance

arXiv: https://arxiv.org/abs/2309.06934 · HTML: https://mlsanity.com/paper/2309.06934/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2023.

## Built on by (most cited first, 9 of 9)

- [Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion](https://mlsanity.com/paper/2310.02279/) (2023)
- [A Survey on Diffusion Models for Inverse Problems](https://mlsanity.com/paper/2410.00083/) (2024)
- [TFG: Unified Training-Free Guidance for Diffusion Models](https://mlsanity.com/paper/2409.15761/) (2024)
- [Zero-Shot Duet Singing Voices Separation with Diffusion Models](https://mlsanity.com/paper/2311.07345/) (2023)
- [Improving Inference-Time Optimisation for Vocal Effects Style Transfer with a Gaussian Prior](https://mlsanity.com/paper/2505.11315/) (2025)
- [WaveLLDM: Design and Development of a Lightweight Latent Diffusion Model for Speech Enhancement and Restoration](https://mlsanity.com/paper/2508.21153/) (2025)
- [Twenty-Five Years of MIR Research: Achievements, Practices, Evaluations, and Future Challenges](https://mlsanity.com/paper/2511.07205/) (2025)
- [Single-step Controllable Music Bandwidth Extension With Flow Matching](https://mlsanity.com/paper/2601.14356/) (2026)
- [SE-MSB: End-to-End Unpaired Speech Enhancement using Mamba Schr"odinger Bridges](https://mlsanity.com/paper/2609.26000/) (2026)

## Abstract (arXiv)

Restoring degraded music signals is essential to enhance audio quality for downstream music manipulation. Recent diffusion-based music restoration methods have demonstrated impressive performance, and among them, diffusion posterior sampling (DPS) stands out given its intrinsic properties, making it versatile across various restoration tasks. In this paper, we identify that there are potential issues which will degrade current DPS-based methods' performance and introduce the way to mitigate the issues inspired by diverse diffusion guidance techniques including the RePaint (RP) strategy and the Pseudoinverse-Guided Diffusion Models (PiGDM). We demonstrate our methods for the vocal declipping and bandwidth extension tasks under various levels of distortion and cutoff frequency, respectively. In both tasks, our methods outperform the current DPS-based music restoration benchmarks. We refer to urlhttp://carlosholivan.github.io/demos/audio-restoration-2023.html for examples of the restored audio samples.