# GAZEV: GAN-Based Zero-Shot Voice Conversion over Non-parallel Speech Corpus

arXiv: https://arxiv.org/abs/2010.12788 · HTML: https://mlsanity.com/paper/2010.12788/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2020.

## Built on by (most cited first, 10 of 10)

- [GenVC: Self-Supervised Zero-Shot Voice Conversion](https://mlsanity.com/paper/2502.04519/) (2025)
- [Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features](https://mlsanity.com/paper/2112.04424/) (2021)
- [SIG-VC: A Speaker Information Guided Zero-shot Voice Conversion System for Both Human Beings and Machines](https://mlsanity.com/paper/2111.03811/) (2021)
- [TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Training](https://mlsanity.com/paper/2208.04035/) (2022)
- [SLMGAN: Exploiting Speech Language Model Representations for Unsupervised Zero-Shot Voice Conversion in GANs](https://mlsanity.com/paper/2307.09435/) (2023)
- [Reimagining Speech: A Scoping Review of Deep Learning-Powered Voice Conversion](https://mlsanity.com/paper/2311.08104/) (2023)
- [Multi-modal Adversarial Training for Zero-Shot Voice Cloning](https://mlsanity.com/paper/2408.15916/) (2024)
- [Generative Adversarial Network based Voice Conversion: Techniques, Challenges, and Recent Advancements](https://mlsanity.com/paper/2504.19197/) (2025)
- [Enhancing Zero-Shot Many to Many Voice Conversion with Self-Attention VAE](https://mlsanity.com/paper/2203.16037/) (2022)
- [Invertible Voice Conversion](https://mlsanity.com/paper/2201.10687/) (2022)

## Abstract (arXiv)

Non-parallel many-to-many voice conversion is recently attract-ing huge research efforts in the speech processing community. A voice conversion system transforms an utterance of a source speaker to another utterance of a target speaker by keeping the content in the original utterance and replacing by the vocal features from the target speaker. Existing solutions, e.g., StarGAN-VC2, present promising results, only when speech corpus of the engaged speakers is available during model training. AUTOVCis able to perform voice conversion on unseen speakers, but it needs an external pretrained speaker verification model. In this paper, we present our new GAN-based zero-shot voice conversion solution, called GAZEV, which targets to support unseen speakers on both source and target utterances. Our key technical contribution is the adoption of speaker embedding loss on top of the GAN framework, as well as adaptive instance normalization strategy, in order to address the limitations of speaker identity transfer in existing solutions. Our empirical evaluations demonstrate significant performance improvement on output speech quality and comparable speaker similarity to AUTOVC.