# R2-SVC: Towards Real-World Robust and Expressive Zero-shot Singing Voice Conversion

arXiv: https://arxiv.org/abs/2510.20677 · HTML: https://mlsanity.com/paper/2510.20677/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 21 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Masking](https://mlsanity.com/paper/2303.00332/) (2023)
- [Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus](https://mlsanity.com/paper/2112.10358/) (2021)
- [Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis](https://mlsanity.com/paper/2201.07429/) (2022)
- [Zero-shot Voice Conversion with Diffusion Transformers](https://mlsanity.com/paper/2411.09943/) (2024)
- [GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks](https://mlsanity.com/paper/2409.13832/) (2024)
- [Mel-Band RoFormer for Music Source Separation](https://mlsanity.com/paper/2310.01809/) (2023)
- [Accent and Speaker Disentanglement in Many-to-many Voice Conversion](https://mlsanity.com/paper/2011.08609/) (2020)
- [Learning the Beauty in Songs: Neural Singing Voice Beautifier](https://mlsanity.com/paper/2202.13277/) (2022)
- [Noise-robust voice conversion with domain adversarial training](https://mlsanity.com/paper/2201.10693/) (2022)
- [SaMoye: Zero-shot Singing Voice Conversion Model Based on Feature Disentanglement and Enhancement](https://mlsanity.com/paper/2407.07728/) (2024)
- [FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion](https://mlsanity.com/paper/2501.05586/) (2025)
- [Toward Degradation-Robust Voice Conversion](https://mlsanity.com/paper/2110.07537/) (2021)
- [REF-VC: Robust, Expressive and Fast Zero-Shot Voice Conversion with Diffusion Transformers](https://mlsanity.com/paper/2508.04996/) (2025)

## Built on by (most cited first, 1 of 1)

- [YingMusic-SVC: Real-World Robust Zero-Shot Singing Voice Conversion with Flow-GRPO and Singing-Specific Inductive Biases](https://mlsanity.com/paper/2512.04793/) (2025)

## Abstract (arXiv)

In real-world singing voice conversion (SVC) applications, environmental noise and the demand for expressive output pose significant challenges. Conventional methods, however, are typically designed without accounting for real deployment scenarios, as both training and inference usually rely on clean data. This mismatch hinders practical use, given the inevitable presence of diverse noise sources and artifacts from music separation. To tackle these issues, we propose R2-SVC, a robust and expressive SVC framework. First, we introduce simulation-based robustness enhancement through random fundamental frequency (F0) perturbations and music separation artifact simulations (e.g., reverberation, echo), substantially improving performance under noisy conditions. Second, we enrich speaker representation using domain-specific singing data: alongside clean vocals, we incorporate DNSMOS-filtered separated vocals and public singing corpora, enabling the model to preserve speaker timbre while capturing singing style nuances. Third, we integrate the Neural Source-Filter (NSF) model to explicitly represent harmonic and noise components, enhancing the naturalness and controllability of converted singing. R2-SVC achieves state-of-the-art results on multiple SVC benchmarks under both clean and noisy conditions.