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

TL;DR

R2-SVC is a novel singing voice conversion framework that enhances robustness to noise and artifacts, improves expressiveness, and achieves state-of-the-art results in real-world noisy environments.

Contribution

It introduces simulation-based robustness, enriched speaker representations, and NSF integration for natural and controllable singing voice conversion.

Findings

State-of-the-art performance under noisy conditions

Improved robustness through data augmentation techniques

Enhanced naturalness and expressiveness of converted singing

Abstract

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 ($F_0$) 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.