Metraipolis › archive › dc_a72d905503d5

Learning to Watermark Speech Synthesis Against Model-Driven Reconstruction — arXiv:2610.04235

Source
arXiv
Original
https://arxiv.org/abs/2610.04235
License (as archived)
CC0-1.0
Archived
2026-10-06T05:29:45.497Z
SHA-256 of the archived text
380a062f1a28416b679ce8a94f590d39bd6560500694a2944a052926c1470ae5
Stable URL of this page
https://metraipolis.com/documento/dc_a72d905503d5

How to cite

Learning to Watermark Speech Synthesis Against Model-Driven Reconstruction — arXiv:2610.04235 — arXiv, https://arxiv.org/abs/2610.04235 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a72d905503d5 (Metraipolis archive dc_a72d905503d5, sha256 380a062f1a28416b679ce8a94f590d39bd6560500694a2944a052926c1470ae5)
BibTeX
@misc{dca72d905503d5,
  title = {Learning to Watermark Speech Synthesis Against Model-Driven Reconstruction — arXiv:2610.04235},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04235},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a72d905503d5; sha256 380a062f1a28416b679ce8a94f590d39bd6560500694a2944a052926c1470ae5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04235. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 synthesized speech. Once released, however, speech may undergo heterogeneous learned transformations during distribution and editing, with reconstruction objectives that can preserve speech utility while affecting watermark recoverability differently. We find that no single watermark carrier remains consistently reliable across reconstruction models, as its survival depends jointly on the embedded structure, reconstruction mechanism, and observation representation. To this end, we propose Thrive, a multi-bit generative speech watermarking framework for modern autoregressive TTS, covering both discrete-token and continuous-representation generation under reconstruction attacks. Specifically, Rise synchronizes watermark injection into intermediate representations with its continued integration into subsequent generation, while Care combines waveform and spectral experts using bit-wise reliability selection. Experiments on both autoregressive paradigms show that Thrive preserves synthesis fidelity, achieves 87.6% average recovery accuracy under reconstruction attacks, and supports source attribution over candidate sets of up to 10,000 identities.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2610.04235 — 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 2026-10-06T05:26:35.333Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).