Metraipolis › archive › dc_b1bf522d37f0

Voice Anonymization Made Simple: Training-Free Anonymization with Projected Classifier-Free Guidance — arXiv:2610.08276

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08276
License (as archived)
CC0-1.0
Archived
2026-10-07T21:22:45.916Z
SHA-256 of the archived text
23d462f8fc19ddaa3b69734ca780953295020b2d1a83d5503d2b1827ccea983c
Stable URL of this page
https://metraipolis.com/documento/dc_b1bf522d37f0

How to cite

Voice Anonymization Made Simple: Training-Free Anonymization with Projected Classifier-Free Guidance — arXiv:2610.08276 — arXiv (en), https://arxiv.org/abs/2610.08276 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b1bf522d37f0 (Metraipolis archive dc_b1bf522d37f0, sha256 23d462f8fc19ddaa3b69734ca780953295020b2d1a83d5503d2b1827ccea983c)
BibTeX
@misc{dcb1bf522d37f0,
  title = {Voice Anonymization Made Simple: Training-Free Anonymization with Projected Classifier-Free Guidance — arXiv:2610.08276},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08276},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b1bf522d37f0; sha256 23d462f8fc19ddaa3b69734ca780953295020b2d1a83d5503d2b1827ccea983c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08276. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Voice anonymization aims to conceal speaker identity while preserving linguistic and paralinguistic information, yet many existing methods require dedicated training. We propose a training-free, two-stage anonymization method for pretrained flow-matching voice conversion systems. In the condition-construction stage, the source content representation is regenerated under a randomly selected speaker context to reduce residual source-speaker information while preserving linguistic content. In the speech-generation stage, the source speech is used to identify the generation direction associated with the original speaker, and the source-aligned component is suppressed while useful content guidance is retained. The proposed method modifies only inference-time conditioning and guidance, without updating any pretrained parameters. Experiments on VoicePrivacy 2026 Track 1 show that the two-stage method improves speaker privacy while maintaining competitive word error rate and emotion recognition performance.

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/2610.08276 — 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 2026-10-07T20:54:04.257Z dalla pagina https://arxiv.org/list/eess.AS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).