提出抗神经编码器的音频水印框架，保障合成语音可溯源性。
CRAW: Codec Robust Audio Watermarking
- 联合畸变感知训练与注意力池化提升鲁棒性
- 在多种神经编码器下仍保持高检测率（>95%）
- 适合用于真实场景中生成语音的版权保护
生成式语音模型使真实与合成音频难以区分，催生新型欺诈与虚假信息。音频水印通过嵌入不可察觉信号，可在事后验证语音来源。然而，现有事后水印方法在神经编码器和降噪器作用下失效，而这些变换常用于实际存储、传输与处理，严重限制其应用。本文提出CRAW框架，同时增强对神经重合成的鲁棒性并保持高感知质量。CRAW结合畸变感知训练、基于注意力的池化机制、推理时感知掩码及纠错码，以恢复鲁棒训练中损失的保真度。实验表明，CRAW在神经编码器、降噪器和声码器下均达到当前最优鲁棒性，且感知质量与现有事后水印方法相当。代码已开源：https://github.com/DavidC1212/craw。
原文摘要 · Abstract (English)
Recent advances in generative speech models have made it increasingly difficult to distinguish authentic from synthetic audio, enabling new forms of fraud and misinformation. Audio watermarking offers a promising defense by embedding an imperceptible signal into generated speech that can later be detected to verify its provenance. However, recent studies have shown that existing post-hoc watermarking methods fail under neural codecs and denoisers, transformations routinely applied during real-world storage, transmission, and processing, severely limiting their practical utility. Here we introduce CRAW, a codec-robust audio watermarking framework that jointly improves robustness against neural re-synthesis while maintaining high perceptual quality. CRAW combines distortion-aware training with an attention-based pooling mechanism, inference-time perceptual mask- ing, and an error-correcting code to recover the fidelity lost during robust training. Experiments demonstrate that CRAW achieves state-of-the-art robustness against neural codecs, denoisers, and vocoders while maintaining perceptual quality comparable to existing post-hoc watermarking methods. The code is available at https://github.com/DavidC1212/craw.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。