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

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 } }