WAKE: Watermarking Audio with Key Enrichment

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xu, Yaoxun, Yu, Jianwei, Chen, Hangting, Wu, Zhiyong, Wu, Xixin, Yu, Dong, Gu, Rongzhi, Luo, Yi
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912417280163840
author Xu, Yaoxun
Yu, Jianwei
Chen, Hangting
Wu, Zhiyong
Wu, Xixin
Yu, Dong
Gu, Rongzhi
Luo, Yi
author_facet Xu, Yaoxun
Yu, Jianwei
Chen, Hangting
Wu, Zhiyong
Wu, Xixin
Yu, Dong
Gu, Rongzhi
Luo, Yi
contents As deep learning advances in audio generation, challenges in audio security and copyright protection highlight the need for robust audio watermarking. Recent neural network-based methods have made progress but still face three main issues: preventing unauthorized access, decoding initial watermarks after multiple embeddings, and embedding varying lengths of watermarks. To address these issues, we propose WAKE, the first key-controllable audio watermark framework. WAKE embeds watermarks using specific keys and recovers them with corresponding keys, enhancing security by making incorrect key decoding impossible. It also resolves the overwriting issue by allowing watermark decoding after multiple embeddings and supports variable-length watermark insertion. WAKE outperforms existing models in both watermarked audio quality and watermark detection accuracy. Code, more results, and demo page: https://thuhcsi.github.io/WAKE.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05891
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WAKE: Watermarking Audio with Key Enrichment
Xu, Yaoxun
Yu, Jianwei
Chen, Hangting
Wu, Zhiyong
Wu, Xixin
Yu, Dong
Gu, Rongzhi
Luo, Yi
Sound
Audio and Speech Processing
As deep learning advances in audio generation, challenges in audio security and copyright protection highlight the need for robust audio watermarking. Recent neural network-based methods have made progress but still face three main issues: preventing unauthorized access, decoding initial watermarks after multiple embeddings, and embedding varying lengths of watermarks. To address these issues, we propose WAKE, the first key-controllable audio watermark framework. WAKE embeds watermarks using specific keys and recovers them with corresponding keys, enhancing security by making incorrect key decoding impossible. It also resolves the overwriting issue by allowing watermark decoding after multiple embeddings and supports variable-length watermark insertion. WAKE outperforms existing models in both watermarked audio quality and watermark detection accuracy. Code, more results, and demo page: https://thuhcsi.github.io/WAKE.
title WAKE: Watermarking Audio with Key Enrichment
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2506.05891