NeuMark: Neural Codec Resynthesis-Robust Audio Watermarking in the Codec Latent Space

2026-09-22

AI Summary

为解决神经编解码器重合成导致的音频水印丢失问题，提出NeuMark框架，在编解码器潜在空间中嵌入水印以增强鲁棒性。

Abstract

Audio watermarking is increasingly important for tracing generated speech. Several audio watermarking methods have been proposed to embed the watermark in various domains, such as waveform, timbre feature, or latent representations, for making the embedded watermark robust against traditional digital signal processing (DSP) attacks. On the other hand, modern neural codecs introduce a different threat from DSP attacks: they resynthesize speech through quantized acoustic representations and can remove the embedded watermark evi- dence that is not aligned with codec-preserved structure. In this paper, we propose NeuMark, a codec-latent audio watermarking framework that embeds watermark evidence into SpeechTok- enizer acoustic tokens to address this resynthesis threat. NeuMark uses cross-attention to inject a 16-bit message across residual vector quantization (RVQ) layers, distributing the watermark over codec-aligned latent structure. Experimental results show that NeuMark substantially improves robustness under neural- codec resynthesis while supporting both watermark detection and message recovery. We also analyze the trade-off between reconstruction-referenced transparency and original-referenced robustness.

Problem

• audio watermarking
• neural codecs
• resynthesis threat
• robustness

Innovation

• Neural Codec
• Audio Watermarking
• Cross-Attention
• Residual Vector Quantization (RVQ)
• Codec Latent Space