# ZSVC: Zero-shot Style Voice Conversion with Disentangled Latent Diffusion Models and Adversarial Training

arXiv: https://arxiv.org/abs/2501.04416 · HTML: https://mlsanity.com/paper/2501.04416/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 26 of its 31 references that are in the map.
- First posted on arXiv 8 Jan 2025.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 26 of 26)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://mlsanity.com/paper/2301.12661/) (2023)
- [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](https://mlsanity.com/paper/1803.09017/) (2018)
- [NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers](https://mlsanity.com/paper/2304.09116/) (2023)
- [emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation](https://mlsanity.com/paper/2312.15185/) (2023)
- [AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss](https://mlsanity.com/paper/1905.05879/) (2019)
- [Emotional Voice Conversion: Theory, Databases and ESD](https://mlsanity.com/paper/2105.14762/) (2021)
- [SoundStorm: Efficient Parallel Audio Generation](https://mlsanity.com/paper/2305.09636/) (2023)
- [Unsupervised Speech Decomposition via Triple Information Bottleneck](https://mlsanity.com/paper/2004.11284/) (2020)
- [One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization](https://mlsanity.com/paper/1904.05742/) (2019)
- [CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training](https://mlsanity.com/paper/1703.10155/) (2017)
- [SpeechSplit 2.0: Unsupervised speech disentanglement for voice conversion Without tuning autoencoder Bottlenecks](https://mlsanity.com/paper/2203.14156/) (2022)
- [Token-Level Ensemble Distillation for Grapheme-to-Phoneme Conversion](https://mlsanity.com/paper/1904.03446/) (2019)
- [StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis](https://mlsanity.com/paper/2312.10741/) (2023)
- [SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention](https://mlsanity.com/paper/2312.08676/) (2023)
- [LM-VC: Zero-shot Voice Conversion via Speech Generation based on Language Models](https://mlsanity.com/paper/2306.10521/) (2023)
- [Disentanglement of Emotional Style and Speaker Identity for Expressive Voice Conversion](https://mlsanity.com/paper/2110.10326/) (2021)
- [Towards Improved Zero-shot Voice Conversion with Conditional DSVAE](https://mlsanity.com/paper/2205.05227/) (2022)
- [METTS: Multilingual Emotional Text-to-Speech by Cross-speaker and Cross-lingual Emotion Transfer](https://mlsanity.com/paper/2307.15951/) (2023)
- [Delivering Speaking Style in Low-resource Voice Conversion with Multi-factor Constraints](https://mlsanity.com/paper/2211.08857/) (2022)

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

- [DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model](https://mlsanity.com/paper/2506.00350/) (2025)
- [ReFlow-VC: Zero-shot Voice Conversion Based on Rectified Flow and Speaker Feature Optimization](https://mlsanity.com/paper/2506.01032/) (2025)
- [Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection](https://mlsanity.com/paper/2605.03039/) (2026)

## Abstract (arXiv)

Style voice conversion aims to transform the speaking style of source speech into a desired style while keeping the original speaker's identity. However, previous style voice conversion approaches primarily focus on well-defined domains such as emotional aspects, limiting their practical applications. In this study, we present ZSVC, a novel Zero-shot Style Voice Conversion approach that utilizes a speech codec and a latent diffusion model with speech prompting mechanism to facilitate in-context learning for speaking style conversion. To disentangle speaking style and speaker timbre, we introduce information bottleneck to filter speaking style in the source speech and employ Uncertainty Modeling Adaptive Instance Normalization (UMAdaIN) to perturb the speaker timbre in the style prompt. Moreover, we propose a novel adversarial training strategy to enhance in-context learning and improve style similarity. Experiments conducted on 44,000 hours of speech data demonstrate the superior performance of ZSVC in generating speech with diverse speaking styles in zero-shot scenarios.