Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions

• URL: http://arxiv.org/abs/2606.11828v1
• Date: Wed, 10 Jun 2026 09:06:37 GMT
• Title: Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions
• Abstract summary: We propose a feature-aligned watermarking method that aligns the watermark with the original speech feature distribution.<n>We use a pretrained speech to generate a pseudo-speech watermark and fuse it into the spectrogram of the input audio, with VAD loss and perceptual losses guiding embedding.<n>Experiments show that our method maintains imperceptibility comparable to existing approaches while substantially improving robustness under both seen and unseen speech reconstruction models.
• Score: 12.934502081353147
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Hidden in Plain Tokens: Simply Robust, Gradient-Free Watermark for Synthetic Audio [58.612001688217056]
  Inference-time watermarks for autoregressive models are unfit for continuous modalities due to discretization inconsistencies.<n>We propose an elegant solution for powerful and robust watermarking of synthetic audio.
  arXiv  Detail & Related papers  (2026-05-25T15:43:20Z)
• ShapeMark: Robust and Diversity-Preserving Watermarking for Diffusion Models [1.531886051127726]
  Noise-as-Watermark (NaW) approaches integrate watermarking directly into the diffusion process.<n>We introduce a dedicated randomization design that reshuffles the positions of noise elements without changing their values.<n>Our method achieves state-of-the-art robustness while maintaining high generation quality across a wide range of lossy scenarios.
  arXiv  Detail & Related papers  (2026-03-10T10:10:47Z)
• Latent-Mark: An Audio Watermark Robust to Neural Resynthesis [62.09761127079914]
  Latent-Mark is the first zero-bit audio watermarking framework designed to survive semantic compression.<n>Our key insight is that robustness to the encode-decode process requires embedding the watermark within the invariant latent space.<n>Our work inspires future research into universal watermarking frameworks capable of maintaining integrity across increasingly complex and diverse generative distortions.
  arXiv  Detail & Related papers  (2026-03-05T15:51:09Z)
• More Haste, Less Speed: Weaker Single-Layer Watermark Improves Distortion-Free Watermark Ensembles [58.941305935872265]
  We show that strong watermarks significantly reduce the entropy of the token distribution.<n>We propose a framework that utilizes weaker single-layer watermarks to preserve the entropy required for effective multi-layer ensembling.
  arXiv  Detail & Related papers  (2026-02-12T10:18:16Z)
• Self Voice Conversion as an Attack against Neural Audio Watermarking [34.948149764638806]
  We investigate self voice conversion as a universal, content-preserving attack against audio watermarking systems.<n>We demonstrate that this attack severely degrades the reliability of state-of-the-art watermarking approaches.
  arXiv  Detail & Related papers  (2026-01-28T09:41:18Z)
• ComMark: Covert and Robust Black-Box Model Watermarking with Compressed Samples [14.929889375744368]
  ComMark is a novel black-box model watermarking framework.<n>We show that ComMark achieves state-of-the-art performance in both covertness and robustness.<n>We extend its applicability beyond image recognition to tasks including speech recognition, sentiment analysis, image generation, image captioning, and video recognition.
  arXiv  Detail & Related papers  (2025-12-16T05:10:32Z)
• StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models [55.05404953041403]
  We propose a novel framework that seamlessly integrates a binary watermark into the diffusion generation process.<n>We show that StableGuard consistently outperforms state-of-the-art methods in image fidelity, watermark verification, and tampering localization.
  arXiv  Detail & Related papers  (2025-09-22T16:35:19Z)
• OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization [66.69924980864053]
  We propose OptMark, an optimization-based approach that embeds a robust multi-bit watermark into the intermediate latents of the diffusion denoising process.<n> OptMark strategically inserts a structural watermark early to resist generative attacks and a detail watermark late to withstand image transformations.<n> Experimental results demonstrate that OptMark achieves invisible multi-bit watermarking while ensuring robust resilience against valuemetric transformations, geometric transformations, editing, and regeneration attacks.
  arXiv  Detail & Related papers  (2025-08-29T15:50:59Z)
• TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity [76.98973481600002]
  This paper proposes a Tamper-Aware Generative image WaterMarking method named TAG-WM.<n>The proposed method comprises four key modules: a dual-mark joint sampling (DMJS) algorithm for embedding copyright and localization watermarks into the latent space while preserving generative quality.<n>The experimental results demonstrate that TAG-WM achieves state-of-the-art performance in both tampering robustness and localization capability even under distortion.
  arXiv  Detail & Related papers  (2025-06-30T03:14:07Z)
• TriniMark: A Robust Generative Speech Watermarking Method for Trinity-Level Attribution [3.1682080884953736]
  We propose a generative textbfspeech wattextbfermarking method (TriniMark) for authenticating the generated content.<n>We first design a structure-lightweight watermark encoder that embeds watermarks into the time-domain features of speech.<n>A temporal-aware gated convolutional network is meticulously designed in the watermark decoder for bit-wise watermark recovery.
  arXiv  Detail & Related papers  (2025-04-29T08:23:28Z)
• A Resilient and Accessible Distribution-Preserving Watermark for Large Language Models [65.40460716619772]
  Our research focuses on the importance of a textbfDistribution-textbfPreserving (DiP) watermark. Contrary to the current strategies, our proposed DiPmark simultaneously preserves the original token distribution during watermarking. It is detectable without access to the language model API and prompts (accessible), and is provably robust to moderate changes of tokens.
  arXiv  Detail & Related papers  (2023-10-11T17:57:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.