Skip to content

Tokens Change, Structure Endures: Spectral Watermarking for Generated Speech

Sep 2026 · arXiv.org · Vol abs/2609.33774 · 0 citations · 45 references
Computer Science Engineering

TL;DR

Redwing is proposed, a design principle for robust token-level watermarking that generalizes to TTS models at a speech-quality cost close to that of KGW and shows that retokenization is not merely a source of noise: its transition structure can be exploited as a design principle for robust token-level watermarking.

Abstract

Watermarking is a promising tool for establishing the provenance of AI-generated speech. While many neural audio watermarking methods rely on a separately trained watermark generator, token-level watermarking is a training-free alternative that operates directly during generation. Its main weakness is retokenization: decoding generated speech to a waveform and encoding it again can change token identities and erode the watermark. To make the watermark robust to these changes, we propose Redwing, REtokenization-Durable Watermarking IN Generation. It builds a graph from the token substitutions observed under retokenization, whose Laplacian yields a basis that assigns similar values to tokens likely to substitute for one another. Over this basis, embedding and detection functions are jointly optimized to preserve watermark signal through retokenization while limiting embedding distortion and detector variability on unwatermarked speech. On the Moshi full-duplex system, after eight consecutive passes of Mimi resynthesis, Redwing achieves 80.7% TPR at a calibrated 1% FPR, compared with 8.3% for KGW and at most 7.3% for WMAR. It also has the highest TPR after eight passes through three other neural codecs (77.5-93.0%), and the gains generalize to TTS models at a speech-quality cost close to that of KGW. These results show that retokenization is not merely a source of noise: its transition structure can be exploited as a design principle for robust token-level watermarking.

View source

Similar papers

Preprint Oct 2026

MARC: Multi-Bit Watermarking for Autoregressive Audio Generation against Codec Attacks

Generated audio is now used in a range of applications, creating a need to verify its origin after distribution and signal processing. This task is particularly challenging for autoregressive audio generation because codec processing can alter the token sequence recovered from the waveform. Such changes reduce the reli...

Liao-Ran Xu, Wei-Zhi Liu, Zhao-Xia Yin · 0 citations
Preprint Oct 2026

NeuMark-Native: Robust Text-to-Speech-Native Watermarking Through Full Utilization of Neural Audio Codec Latent Space

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...

An-Nan Wu, Wen-Chin Huang, T. Toda · 0 citations
Sep 2026

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

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...

An-Nan Wu, Wen-Chin Huang, T. Toda · 1 citation
Preprint Oct 2026

Learning to Watermark Speech Synthesis Against Model-Driven Reconstruction

Modern TTS systems increasingly generate synthetic speech at scale for diverse users. This setting calls for content-level provenance that can verify the origin of released speech and attribute it to the requesting user, which generative watermarking can support by embedding multi-bit identifiers directly into synthesi...

Wei-Zhi Liu, Yue Li, Hui Tian et al. · 0 citations
Preprint Sep 2026

The Vulnerability of Neural Audio Watermarks under Speech Enhancement

Neural audio watermarks are increasingly deployed in commercial speech generation systems to make AI-generated speech traceable, yet their robustness has been studied mainly under conventional signal distortions. Since a watermark can be regarded as imperceptible noise added to the speech signal, a natural question is...

Xin Zhong, Sheng-Yao Wang, Ling-Feng Yao et al. · 1 citation
Preprint Aug 2026

Combining Self-Embedding Audio Watermarking with Ultra-Low-Bitrate Neural Codecs

Experiments across four controlled manipulation types under ideal channel conditions show that the embedded payload, and hence an approximate reconstruction of the authentic content, is always fully recovered without bit errors, and the results indicate that the choice of neural codec is the dominant factor for detecti...

Yigitcan Özer, Xin Wang, Zhe Zhang et al. · 0 citations

Related blog posts

Microsoft Research Blog Nov 3, 2026

Learn the rules: The hacker mindset

Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.

MIT News · Artificial Intelligence Aug 27, 2026

Looking beyond natural sequences

A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.