ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2505.21568
68
0
v1v2 (latest)

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents

27 May 2025
Haiyun Li
Zhiyong Wu
Xiaofeng Xie
Jingran Xie
Yaoxun Xu
Hanyang Peng
ArXiv (abs)PDFHTML
Main:4 Pages
3 Figures
Bibliography:1 Pages
3 Tables
Abstract

Voice cloning (VC)-resistant watermarking is an emerging technique for tracing and preventing unauthorized cloning. Existing methods effectively trace traditional VC models by training them on watermarked audio but fail in zero-shot VC scenarios, where models synthesize audio from an audio prompt without training. To address this, we propose VoiceMark, the first zero-shot VC-resistant watermarking method that leverages speaker-specific latents as the watermark carrier, allowing the watermark to transfer through the zero-shot VC process into the synthesized audio. Additionally, we introduce VC-simulated augmentations and VAD-based loss to enhance robustness against distortions. Experiments on multiple zero-shot VC models demonstrate that VoiceMark achieves over 95% accuracy in watermark detection after zero-shot VC synthesis, significantly outperforming existing methods, which only reach around 50%. See our code and demos at: this https URL

View on arXiv
@article{li2025_2505.21568,
  title={ VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents },
  author={ Haiyun Li and Zhiyong Wu and Xiaofeng Xie and Jingran Xie and Yaoxun Xu and Hanyang Peng },
  journal={arXiv preprint arXiv:2505.21568},
  year={ 2025 }
}
Comments on this paper