Multi-bit Audio Watermarking
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912623212101632 |
|---|---|
| author | Lanzendörfer, Luca A. Fearne, Kyle Grötschla, Florian Wattenhofer, Roger |
| author_facet | Lanzendörfer, Luca A. Fearne, Kyle Grötschla, Florian Wattenhofer, Roger |
| contents | We present Timbru, a post-hoc audio watermarking model that achieves state-of-the-art robustness and imperceptibility trade-offs without training an embedder-detector model. Given any 44.1 kHz stereo music snippet, our method performs per-audio gradient optimization to add imperceptible perturbations in the latent space of a pretrained audio VAE, guided by a combined message and perceptual loss. The watermark can then be extracted using a pretrained CLAP model. We evaluate 16-bit watermarking on MUSDB18-HQ against AudioSeal, WavMark, and SilentCipher across common filtering, noise, compression, resampling, cropping, and regeneration attacks. Our approach attains the best average bit error rates, while preserving perceptual quality, demonstrating an efficient, dataset-free path to imperceptible audio watermarking. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01968 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-bit Audio Watermarking Lanzendörfer, Luca A. Fearne, Kyle Grötschla, Florian Wattenhofer, Roger Sound Machine Learning Audio and Speech Processing We present Timbru, a post-hoc audio watermarking model that achieves state-of-the-art robustness and imperceptibility trade-offs without training an embedder-detector model. Given any 44.1 kHz stereo music snippet, our method performs per-audio gradient optimization to add imperceptible perturbations in the latent space of a pretrained audio VAE, guided by a combined message and perceptual loss. The watermark can then be extracted using a pretrained CLAP model. We evaluate 16-bit watermarking on MUSDB18-HQ against AudioSeal, WavMark, and SilentCipher across common filtering, noise, compression, resampling, cropping, and regeneration attacks. Our approach attains the best average bit error rates, while preserving perceptual quality, demonstrating an efficient, dataset-free path to imperceptible audio watermarking. |
| title | Multi-bit Audio Watermarking |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2510.01968 |