Metraipolis › archive › dc_69f06dc47654
WST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection — arXiv:2609.29372
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29372
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:27:28.448Z
- SHA-256 of the archived text
95e417eaa8bb281d0c61eb074212c7539de7d34fdfcd6fb70cedd9e49a5f94c2- Stable URL of this page
https://metraipolis.com/documento/dc_69f06dc47654
How to cite
WST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection — arXiv:2609.29372 — arXiv (en), https://arxiv.org/abs/2609.29372 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_69f06dc47654 (Metraipolis archive dc_69f06dc47654, sha256 95e417eaa8bb281d0c61eb074212c7539de7d34fdfcd6fb70cedd9e49a5f94c2)
BibTeX
@misc{dc69f06dc47654,
title = {WST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection — arXiv:2609.29372},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29372},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_69f06dc47654; sha256 95e417eaa8bb281d0c61eb074212c7539de7d34fdfcd6fb70cedd9e49a5f94c2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29372. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The acoustic front-end determines which forensic cues a speech deepfake detector can exploit. The wavelet scattering transform (WST) provides stable multiscale coefficients with explicit coordinates, yet direct flattening obscures the parent relation between paths. We introduce WST-Graph, reconstructing these paths as a sparse modulation-carrier grid for an AASIST graph backend. Modulation-level normalization and length-aware adaptive local attention pooling produce fixed relative-time representations while retaining the acoustic axes before learned adaptation. This yields a waveform-to-graph interface with a fixed, parameter-free WST. Our configurations remain competitive with AASIST while using approximately 60% fewer trainable parameters and show clear gains on selected out-of-domain benchmarks. These results underscore the value of preserving parent-child relations within the carrier-modulation topology when constructing a compact, physically grounded interface for graph-based speech deepfake detection. Code will be released at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI). Categorie arXiv: Audio and Speech Processing (eess.AS) ; Artificial Intelligence (cs.AI); Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2609.29372 — 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 2026-10-08T03:50:58.051Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).