Robust and Imperceptible Watermarking Framework for Generative Audio Models
IEEE Signal Processing Letters · 2025 · 32 · 3196-3200
DOI: 10.1109/lsp.2025.3596015 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2025. Verfasst von Yan Feng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: Donghua University 2025 Cultivation Project of Discipline Innovation.
Abstract (Originalsprache)
The rapid development of generative audio models has raised concerns about copyright protection and traceability. To tackle these challenges, we first propose a robust and imperceptible watermarking framework embedded directly into the generative process. Our method embeds watermarks into the convolutional layers of the generative model, allowing the synthesis of watermarked audio without compromising quality. A trainable binary mask selectively modulates kernel weights, ensuring precise and efficient embedding. The framework incorporates a dedicated encoder-decoder architecture for accurate watermark embedding and extraction. A normalization step aligns the modified kernel weights with the original statistical properties to preserve the model’s performance. Experimental results across multiple datasets demonstrate the method’s robustness against common audio attacks. Additionally, the approach achieves high audio fidelity and near-perfect watermark recovery, offering a practical solution for traceable and secure audio synthesis.
Förderung
- Donghua University 2025 Cultivation Project of Discipline Innovation
Zitieren
APA
Feng, Y., Zhang, X., Feng, F., Zhang, G., & Xu, L. (2025). Robust and Imperceptible Watermarking Framework for Generative Audio Models. IEEE Signal Processing Letters, 32, 3196-3200. https://doi.org/10.1109/lsp.2025.3596015
Vancouver
Feng Y, Zhang X, Feng F, Zhang G, Xu L. Robust and Imperceptible Watermarking Framework for Generative Audio Models. IEEE Signal Processing Letters. 2025;32:3196-3200. doi:10.1109/lsp.2025.3596015
BibTeX
@article{Feng2025,
author = {Feng, Yan and Zhang, Xuebin and Feng, Fuyuan and Zhang, Guanglin and Xu, Longting},
title = {Robust and Imperceptible Watermarking Framework for Generative Audio Models},
journal = {IEEE Signal Processing Letters},
year = {2025},
volume = {32},
pages = {3196--3200},
doi = {10.1109/lsp.2025.3596015}
}
EUVIMED