Metraipolis › archive › dc_b1f448db119d

Tracing Decoder Artifacts for Compact Synthetic Speech Screening — arXiv:2609.32050

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32050
License (as archived)
CC0-1.0
Archived
2026-10-07T20:59:49.888Z
SHA-256 of the archived text
14fcd66e80b9fe763bf6a58d14d1efc56c3d42d01f3699ea6fd8d55072d263f7
Stable URL of this page
https://metraipolis.com/documento/dc_b1f448db119d

How to cite

Tracing Decoder Artifacts for Compact Synthetic Speech Screening — arXiv:2609.32050 — arXiv (en), https://arxiv.org/abs/2609.32050 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b1f448db119d (Metraipolis archive dc_b1f448db119d, sha256 14fcd66e80b9fe763bf6a58d14d1efc56c3d42d01f3699ea6fd8d55072d263f7)
BibTeX
@misc{dcb1f448db119d,
  title = {Tracing Decoder Artifacts for Compact Synthetic Speech Screening — arXiv:2609.32050},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32050},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b1f448db119d; sha256 14fcd66e80b9fe763bf6a58d14d1efc56c3d42d01f3699ea6fd8d55072d263f7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32050. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in speech synthesis and voice cloning have increased the need for reliable synthetic-speech detection, yet high-accuracy detectors increasingly rely on large pretrained models that are costly to invoke on every recording. Rather than replacing such detectors, we investigate a compact front-end screen that processes all inputs cheaply and forwards only suspicious recordings for more expensive analysis. To enable lightweight screening without a large learned encoder, we exploit spectral traces introduced by speech-generation operations. We analyze how learned upsampling and inverse short-time Fourier transform synthesis can produce predictable spectral artifacts and measure their presence directly in generated waveforms. Because the strength of these artifacts varies across generators, we combine decoder-guided spectral measurements with complementary descriptors of short-time spectral shape and temporal variation in a compact gradient-boosted tree. Across seven speech generators and two human-speech sources, the proposed screen achieves an equal error rate of 0.021\% with an estimated model storage of 151 KiB. When used as the first stage of a simulated cascade with a 1.15-billion-parameter detector, it reduces estimated detection energy by 84.4\% while operating at a 0.050\% synthetic-speech miss rate, demonstrating the potential of decoder-guided acoustic evidence for low-cost front-end screening.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.32050 — 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 2026-10-07T20:29:02.216Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).