AudioNoisePrints is a training‑free audio watermarking pipeline designed for flow‑matching and diffusion TTS models. It leverages strong spatial correlations between the initial Gaussian noise and the generated output, using a simple cosine correlation to embed the watermark while adding minimal inference overhead. A lightweight detector is trained to handle aggressive augmentations, and the method outperforms the AudioSeal baseline on F5TTS and other TTS/vocoder models, indicating broad applicability to flow‑matching TTS and potentially vocoders.
arXiv:2603. 05310v3 Announce Type: replace-cross Abstract: While existing audio watermarking techniques have achieved strong robustness against traditional digital signal processing (DSP) attacks, they remain vulnerable to neural compression.
The paper introduces CRAW, a codec‑robust audio watermarking framework designed to embed imperceptible signals into synthetic speech. CRAW enhances robustness against neural re‑synthesis, codecs, denoisers, and vocoders while preserving high perceptual quality through distortion‑aware training, attention‑based pooling, perceptual masking, and error‑correcting codes. Experiments show CRAW outperforms existing post‑hoc watermarking methods in robustness without compromising audio quality.
CRAW is a codec‑robust audio watermarking framework designed to embed imperceptible signals into synthetic speech, enabling provenance verification. It improves robustness against neural re‑synthesis, codecs, denoisers, and vocoders while preserving perceptual quality through distortion‑aware training, attention‑based pooling, perceptual masking, and error‑correcting codes. Experiments show CRAW outperforms existing post‑hoc watermarking methods in robustness without compromising audio quality.
The paper introduces mAVE, a training‑free watermarking framework for joint audio‑visual diffusion transformers that binds audio and video modalities through a session‑keyed cryptographic digest. mAVE separates public record retrieval from secret session authentication, enabling provider‑assisted verification without altering generator weights or training auxiliary networks. Experiments on LTX‑2 and MOVA demonstrate high true‑positive rates (99.8%) and negligible false positives, while maintaining comparable generation quality.
The paper introduces Traceable TTS, a framework that enables Text‑to‑Speech systems to attribute synthesized speech to their source models without embedding explicit watermarks. By jointly training the TTS model and a discriminator, the method improves traceability generalization while maintaining or slightly enhancing audio quality. This represents the first attempt at watermark‑free TTS with strong traceability, and the authors plan to release the code to support further research.
arXiv:2606. 11828v1 Announce Type: cross Abstract: Audio watermarking aims to embed identifiable information into audio while remaining imperceptible.
arXiv:2607. 11117v1 Announce Type: cross Abstract: AI music generation has rapidly advanced alongside commercial platforms, raising the need for reliable watermarking for provenance and attribution.
The paper introduces RAIN, a lightweight, prompt‑free extractor for semantic watermarks in diffusion models. By decomposing the endpoint recovery into an image‑like anchor and a noise‑oriented residual, RAIN avoids iterative inversion and reduces the computational cost compared to existing one‑step methods. The approach leverages extended flow matching and conditional regression to recover a useful noise statistic near the high‑SNR image endpoint, enabling efficient one‑step extraction.
AI music generation has rapidly advanced alongside commercial platforms, raising the need for reliable watermarking for provenance and attribution. However, existing audio watermarking research has largely focused on speech, and applying speech-oriented methods to music is challenging due to music's complex structure and rich acoustic texture.
Audio watermarking aims to embed identifiable information into audio while remaining imperceptible. Existing methods adopt high-fidelity, low-energy designs to preserve perceptual quality, but the resulting watermarks lack robustness under suppression by speech reconstruction models.
arXiv:2606. 23335v2 Announce Type: replace-cross Abstract: Provenance watermarking is increasingly treated as a safeguard for synthetic speech, whether built directly into speech-generation models such as Chatterbox, provided through dedicated techniques such as AudioSeal, or deployed by commercial platforms such as ElevenLabs.
arXiv:2607. 09134v1 Announce Type: cross Abstract: Representation alignment (REPA) has been investigated to accelerate diffusion training, but we observe that regularizing intermediate representations in diffusion Transformers (DiT) may implicitly entangle latents and limit generative capacity.