Metraipolis › archive › dc_e769dbab3820

Tracing and Relearning Detection Evidence in Text-to-Speech Systems — arXiv:2609.30983

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30983
License (as archived)
CC0-1.0
Archived
2026-10-08T04:19:23.752Z
SHA-256 of the archived text
fadaf94435cece5dbc41909ecb36cf00b3f78d068fcbdd51998bdac6b70553e4
Stable URL of this page
https://metraipolis.com/documento/dc_e769dbab3820

How to cite

Tracing and Relearning Detection Evidence in Text-to-Speech Systems — arXiv:2609.30983 — arXiv (en), https://arxiv.org/abs/2609.30983 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e769dbab3820 (Metraipolis archive dc_e769dbab3820, sha256 fadaf94435cece5dbc41909ecb36cf00b3f78d068fcbdd51998bdac6b70553e4)
BibTeX
@misc{dce769dbab3820,
  title = {Tracing and Relearning Detection Evidence in Text-to-Speech Systems — arXiv:2609.30983},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30983},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e769dbab3820; sha256 fadaf94435cece5dbc41909ecb36cf00b3f78d068fcbdd51998bdac6b70553e4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30983. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent audio deepfake detectors separate bona fide speech from synthetic speech, yet it remains unclear which stage of a text-to-speech system supplies the detection evidence. We address this with controlled resynthesis and detector adaptation in an F5-TTS-BigVGAN pipeline. Since vocoder reconstruction of a real mel can itself be separable from the source utterance, we fix the vocoder and trace the larger change in detector separation to acoustic generation. Adversarially fine-tuning the acoustic model, with no detector in its objective, raises EER against fixed detectors at comparable quality. However, adapting a detector only on the tuned model's VCTK outputs lowers its LibriSpeech EER from 19.42% to 7.46% and improves detection of unseen base F5-TTS outputs. These results suggest that acoustic-model updates can reduce the detection evidence available to fixed detectors, while detector adaptation keeps the updated outputs detectable in this pipeline.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in eess.AS).
Categorie arXiv: Sound (cs.SD) ; Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.30983 — 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 2026-10-08T03:50:06.043Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).