# Robust One-Shot Singing Voice Conversion

arXiv: https://arxiv.org/abs/2210.11096 · HTML: https://mlsanity.com/paper/2210.11096/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 59 references that are in the map.
- First posted on arXiv 20 Oct 2022.

## Builds on (most cited first, 30 of 46)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [WaveGrad: Estimating Gradients for Waveform Generation](https://mlsanity.com/paper/2009.00713/) (2020)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis](https://mlsanity.com/paper/1910.06711/) (2019)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [Adversarial Audio Synthesis](https://mlsanity.com/paper/1802.04208/) (2018)
- [Efficient Neural Audio Synthesis](https://mlsanity.com/paper/1802.08435/) (2018)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022)
- [SampleRNN: An Unconditional End-to-End Neural Audio Generation Model](https://mlsanity.com/paper/1612.07837/) (2016)
- [One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization](https://mlsanity.com/paper/1904.05742/) (2019)
- [PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior](https://mlsanity.com/paper/2106.06406/) (2021)
- [The Unusual Effectiveness of Averaging in GAN Training](https://mlsanity.com/paper/1806.04498/) (2018)
- [StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion](https://mlsanity.com/paper/2107.10394/) (2021)
- [WaveFlow: A Compact Flow-based Model for Raw Audio](https://mlsanity.com/paper/1912.01219/) (2019)
- [AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization](https://mlsanity.com/paper/2011.00316/) (2020)
- [The 2018 Signal Separation Evaluation Campaign](https://mlsanity.com/paper/1804.06267/) (2018)
- [DiffSVC: A Diffusion Probabilistic Model for Singing Voice Conversion](https://mlsanity.com/paper/2105.13871/) (2021)
- [FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention](https://mlsanity.com/paper/2010.14150/) (2020)
- [SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping](https://mlsanity.com/paper/2203.16749/) (2022)
- [VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture](https://mlsanity.com/paper/2006.04154/) (2020)

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

- [GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks](https://mlsanity.com/paper/2409.13832/) (2024)
- [SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANs](https://mlsanity.com/paper/2307.09435/) (2023)
- [Iteratively Improving Speech Recognition and Voice Conversion](https://mlsanity.com/paper/2305.15055/) (2023)
- [SingVisio: Visual Analytics of Diffusion Model for Singing Voice Conversion](https://mlsanity.com/paper/2402.12660/) (2024)
- [LOCKEY: A Novel Approach to Model Authentication and Deepfake Tracking](https://mlsanity.com/paper/2409.07743/) (2024)
- [Degrading Voice: A Comprehensive Overview of Robust Voice Conversion Through Input Manipulation](https://mlsanity.com/paper/2512.06304/) (2025)

## Abstract (arXiv)

Recent progress in deep generative models has improved the quality of voice conversion in the speech domain. However, high-quality singing voice conversion (SVC) of unseen singers remains challenging due to the wider variety of musical expressions in pitch, loudness, and pronunciation. Moreover, singing voices are often recorded with reverb and accompaniment music, which make SVC even more challenging. In this work, we present a robust one-shot SVC (ROSVC) that performs any-to-any SVC robustly even on such distorted singing voices. To this end, we first propose a one-shot SVC model based on generative adversarial networks that generalizes to unseen singers via partial domain conditioning and learns to accurately recover the target pitch via pitch distribution matching and AdaIN-skip conditioning. We then propose a two-stage training method called Robustify that train the one-shot SVC model in the first stage on clean data to ensure high-quality conversion, and introduces enhancement modules to the encoders of the model in the second stage to enhance the feature extraction from distorted singing voices. To further improve the voice quality and pitch reconstruction accuracy, we finally propose a hierarchical diffusion model for singing voice neural vocoders. Experimental results show that the proposed method outperforms state-of-the-art one-shot SVC baselines for both seen and unseen singers and significantly improves the robustness against distortions.