发表机构
Nagoya University（名古屋大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
NeuMark-Native提出一种TTS原生水印框架，在神经编解码器潜在空间中嵌入载荷，提升水印在DSP和编解码器攻击下的持久性，同时保持语音质量。
AI 中文摘要
语音水印为合成语音提供了主动的可追溯性，然而现有的大多数模型仅在文本到语音（TTS）合成之后，通过向生成的波形添加水印扰动来运行。这种事后设计使水印成为可省略或可绕过的外部步骤，并将水印限制在浅层波形表示中。我们提出了NeuMark-Native，一种面向基于神经编解码器合成的TTS原生水印框架。它在波形解码之前，将载荷信息嵌入到每个生成的编解码器潜在层中，从而提高了水印在下游数字信号处理（DSP）和神经编解码器再合成下的持久性。NeuMark-Native保持预训练的TTS模型和神经编解码器冻结，仅优化生成编解码器令牌上的水印模块。在两个语料库上，针对11种DSP攻击和9种神经编解码器攻击的实验表明，该框架在保持自然度、可懂度和接近合成语音的语音质量的同时，实现了鲁棒的水印检测。
英文摘要
Speech watermarking offers proactive traceability for synthetic speech, yet most existing models operate only after text-to-speech (TTS) synthesis by adding a watermark perturbation to the generated waveform. This post-hoc design leaves watermarking as an external step that can be omitted or bypassed and restricts the watermark to a shallow waveform representation. We propose NeuMark-Native, a TTS-native watermarking framework for neural codec-based synthesis. It embeds payload information into every generated codec-latent layer before waveform decoding, improving watermark persistence under downstream digital signal processing (DSP) and neural codec resynthesis. NeuMark-Native keeps the pretrained TTS model and the neural codec frozen, while optimizing only the watermark modules on generated codec tokens. Experiments on two corpora under 11 DSP attacks and 9 neural-codec attacks demonstrate robust watermark detection while preserving naturalness, intelligibility, and speech quality close to synthetic speech.
