Metraipolis › archive › dc_777396bd1124

Cross-Codec Robustness in Speech Watermarking — arXiv:2611.04716

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04716
License (as archived)
CC0-1.0
Archived
2026-11-04T19:14:22.381Z
SHA-256 of the archived text
add7d1ff41eb01029f099fd4700d86a286bc9cf4e3bd17989e77996302ab6765
Stable URL of this page
https://metraipolis.com/documento/dc_777396bd1124

How to cite

Cross-Codec Robustness in Speech Watermarking — arXiv:2611.04716 — arXiv (en), https://arxiv.org/abs/2611.04716 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_777396bd1124 (Metraipolis archive dc_777396bd1124, sha256 add7d1ff41eb01029f099fd4700d86a286bc9cf4e3bd17989e77996302ab6765)
BibTeX
@misc{dc777396bd1124,
  title = {Cross-Codec Robustness in Speech Watermarking — arXiv:2611.04716},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04716},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_777396bd1124; sha256 add7d1ff41eb01029f099fd4700d86a286bc9cf4e3bd17989e77996302ab6765},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04716. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative speech models synthesize audio that is difficult to distinguish from human recordings. Synthetic speech can be watermarked as a proactive disclosure method, but watermarking models remain vulnerable to resynthesis attacks using neural audio codecs. This article investigates speech watermarking robustness across neural codec and digital signal processing attacks, when specific neural codecs are used for channel augmentation during training. We also present a novel zero-bit watermarking system that uses Descript Audio Codec as the generator. Our results demonstrate that the choice of augmentation codec significantly influences robustness generalization. Experiments show that augmentation with low-bitrate, high-quality neural codecs-Mimi and SNAC-results in promising robustness against unseen neural codecs and traditional attacks with limited quality impact.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv eess.AS, nuovi lavori del giorno).
Categorie arXiv: Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2611.04716 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T18:48:52.643Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).