Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2602.02980 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913074713198592 |
|---|---|
| author | Xuan, Xi Carbone, Davide Zhang, Wenxin Pandey, Ruchi Kinnunen, Tomi H. |
| author_facet | Xuan, Xi Carbone, Davide Zhang, Wenxin Pandey, Ruchi Kinnunen, Tomi H. |
| contents | In this work, we focus on front-end design for speech deepfake detectors, the component that determines the discriminative acoustic cues provided to the classifier. Existing approaches are primarily categorized into two types. Hand-crafted filterbank features are transparent but limited in capturing higher-level information. SSL features, in turn, lack interpretability and may overlook fine-grained spectral anomalies. We propose the WST-X series, a novel family of feature extractors that combines the best of both worlds via the wavelet scattering transform (WST), which cascades wavelet convolutions with modulus nonlinearities to produce deformation-stable, multi-scale features. Experiments on the recent Deepfake-Eval-2024 benchmark, together with cross-dataset evaluations on the SpoofCeleb and In-the-Wild, show that WST-X outperforms existing front-ends by a wide margin. Our analysis reveals that a small averaging scale ($J$), combined with high-frequency and directional resolutions ($Q$, $L$), is critical for capturing subtle artifacts. This underscores the value of stable and translation-invariant features for speech deepfake detection. The code is available at https://github.com/xxuan-acoustics/WST-X-Series. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_02980 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WST-X Series: Wavelet Scattering Transform for Interpretable Speech Deepfake Detection Xuan, Xi Carbone, Davide Zhang, Wenxin Pandey, Ruchi Kinnunen, Tomi H. Audio and Speech Processing Computation and Language Signal Processing In this work, we focus on front-end design for speech deepfake detectors, the component that determines the discriminative acoustic cues provided to the classifier. Existing approaches are primarily categorized into two types. Hand-crafted filterbank features are transparent but limited in capturing higher-level information. SSL features, in turn, lack interpretability and may overlook fine-grained spectral anomalies. We propose the WST-X series, a novel family of feature extractors that combines the best of both worlds via the wavelet scattering transform (WST), which cascades wavelet convolutions with modulus nonlinearities to produce deformation-stable, multi-scale features. Experiments on the recent Deepfake-Eval-2024 benchmark, together with cross-dataset evaluations on the SpoofCeleb and In-the-Wild, show that WST-X outperforms existing front-ends by a wide margin. Our analysis reveals that a small averaging scale ($J$), combined with high-frequency and directional resolutions ($Q$, $L$), is critical for capturing subtle artifacts. This underscores the value of stable and translation-invariant features for speech deepfake detection. The code is available at https://github.com/xxuan-acoustics/WST-X-Series. |
| title | WST-X Series: Wavelet Scattering Transform for Interpretable Speech Deepfake Detection |
| topic | Audio and Speech Processing Computation and Language Signal Processing |
| url | https://arxiv.org/abs/2602.02980 |