2606.11828v1 Jun 10, 2026 cs.SD

Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions

Haiyun Li
Haiyun Li
Citations: 11
h-index: 2
Zhiyong Wu
Zhiyong Wu
Citations: 6
h-index: 1
Zhisheng Zhang
Zhisheng Zhang
Citations: 33
h-index: 3
S. Peng
S. Peng
Citations: 0
h-index: 0
Jingran Xie
Jingran Xie
Citations: 25
h-index: 3
Xiao Xie
Xiao Xie
Citations: 2
h-index: 1
Hanyang Peng
Hanyang Peng
Citations: 42
h-index: 4

Audio watermarking aims to embed identifiable information into audio while remaining imperceptible. Existing methods adopt high-fidelity, low-energy designs to preserve perceptual quality, but the resulting watermarks lack robustness under suppression by speech reconstruction models. Improving robustness is challenging due to the inherent robustness-fidelity trade-off in existing designs, where increasing watermark energy improves robustness but reduces fidelity. To address this problem, we propose a feature-aligned watermarking method that aligns the watermark with the original speech feature distribution, allowing higher watermark energy to improve robustness while preserving imperceptibility. We use a pretrained speech codec to generate a pseudo-speech watermark and fuse it into the spectrogram of the input audio, with VAD loss and perceptual losses guiding embedding within voiced regions. Experiments show that our method maintains imperceptibility comparable to existing approaches while substantially improving robustness under both seen and unseen speech reconstruction models.

0 Citations
0 Influential
2 Altmetric
10.0 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!