CRAW：编解码器鲁棒音频水印

中文摘要 AI 辅助

近期生成式语音模型的进展使得区分真实音频与合成音频愈发困难，催生了新的欺诈与虚假信息形式。音频水印通过在生成语音中嵌入不可感知的信号，后续可检测该信号以验证来源，是一种颇具前景的防御手段。然而，现有事后水印方法在神经编解码器和去噪器下失效，而这些变换是实际存储、传输和处理过程中常规应用的操作，严重限制了其实际应用。本文提出CRAW，一种编解码器鲁棒音频水印框架，可在保持高感知质量的同时，共同提升对神经重合成的鲁棒性。CRAW结合了感知失真感知训练、基于注意力的池化机制、推理时感知掩码以及纠错码，以恢复鲁棒训练过程中损失的保真度。实验表明，CRAW在保持与现有事后水印方法相当的感知质量的同时，实现了对神经编解码器、去噪器和声码器的最先进鲁棒性。代码可在指定URL获取。

英文摘要

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.

发表机构

• Bar-Ilan University（巴伊兰大学）
• NVIDIA（英伟达公司）

机构由 AI 辅助整理，请以论文原文为准。