analiza aiqbench
This research introduces a feature-aligned watermarking technique that resolves the traditional robustness-fidelity trade-off by embedding higher-energy signals within speech feature distributions without compromising perceptual quality. By leveraging pretrained speech codecs and perceptual loss functions, the method significantly enhances resilience against suppression by both known and unknown speech reconstruction models. This advancement offers a practical solution for maintaining audio integrity and copyright protection in an era of sophisticated generative audio tools.
Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions
arXiv:2606.11828v1 Announce Type: cross Abstract: 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.
Abstract: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.
Sound (cs.SD); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Multimedia (cs.MM)
arXiv:2606.11828 [cs.SD]
(or arXiv:2606.11828v1 [cs.SD] for this version)
https://doi.org/10.48550/arXiv.2606.11828 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 243 cuvinte
Subiecte conexe
Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognition
arXiv · 6 iun. 2026
AP-GRPO: Anchor-Gated Phonetic Alignment with Policy Optimization for Pathological Speech Reconstruction
arXiv · 16 iun. 2026
Time-Frequency Consistency Learning for Robust Speech Deepfake Detection
arXiv · 21 iul. 2026
Tokens Change, Structure Endures: Spectral Watermarking for Generated Speech
arXiv · 30 sept. 2026