# Toward Degradation-Robust Voice Conversion

arXiv: https://arxiv.org/abs/2110.07537 · HTML: https://mlsanity.com/paper/2110.07537/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 14 Oct 2021.

## Builds on (most cited first, 20 of 20)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss](https://mlsanity.com/paper/1905.05879/) (2019)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [WHAM!: Extending Speech Separation to Noisy Environments](https://mlsanity.com/paper/1907.01160/) (2019)
- [LibriMix: An Open-Source Dataset for Generalizable Speech Separation](https://mlsanity.com/paper/2005.11262/) (2020)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization](https://mlsanity.com/paper/1904.05742/) (2019)
- [StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks](https://mlsanity.com/paper/1806.02169/) (2018)
- [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)
- [Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations](https://mlsanity.com/paper/1804.02812/) (2018)
- [Defending Your Voice: Adversarial Attack on Voice Conversion](https://mlsanity.com/paper/2005.08781/) (2020)
- [S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations](https://mlsanity.com/paper/2104.02901/) (2021)
- [How Far Are We from Robust Voice Conversion: A Survey](https://mlsanity.com/paper/2011.12063/) (2020)
- [Voicy: Zero-Shot Non-Parallel Voice Conversion in Noisy Reverberant Environments](https://mlsanity.com/paper/2106.08873/) (2021)

## Built on by (most cited first, 3 of 3)

- [REF-VC: Robust, Expressive and Fast Zero-Shot Voice Conversion with Diffusion Transformers](https://mlsanity.com/paper/2508.04996/) (2025)
- [Noro: Noise-Robust One-shot Voice Conversion with Hidden Speaker Representation Learning](https://mlsanity.com/paper/2411.19770/) (2024)
- [R2-SVC: Towards Real-World Robust and Expressive Zero-shot Singing Voice Conversion](https://mlsanity.com/paper/2510.20677/) (2025)

## Abstract (arXiv)

Any-to-any voice conversion technologies convert the vocal timbre of an utterance to any speaker even unseen during training. Although there have been several state-of-the-art any-to-any voice conversion models, they were all based on clean utterances to convert successfully. However, in real-world scenarios, it is difficult to collect clean utterances of a speaker, and they are usually degraded by noises or reverberations. It thus becomes highly desired to understand how these degradations affect voice conversion and build a degradation-robust model. We report in this paper the first comprehensive study on the degradation robustness of any-to-any voice conversion. We show that the performance of state-of-the-art models nowadays was severely hampered given degraded utterances. To this end, we then propose speech enhancement concatenation and denoising training to improve the robustness. In addition to common degradations, we also consider adversarial noises, which alter the model output significantly yet are human-imperceptible. It was shown that both concatenations with off-the-shelf speech enhancement models and denoising training on voice conversion models could improve the robustness, while each of them had pros and cons.