WST-X Series: Wavelet Scattering Transform for Interpretable Speech Deepfake Detection
Deepfake Lab
3 February 04, 2026

WST-X Series: Wavelet Scattering Transform for Interpretable Speech Deepfake Detection

Evidence Level
2/5

How much verified proof exists for this claim

One strong evidence source: arxiv

Mystery Factor
2/5

How intriguing or unexplained this claim is

The claim involves a technical innovation in deepfake detection with some emerging narrative and minor uncertainties about its effectiveness and interpretability, but it is grounded in a well-documented field with clear objectives.

Designing front-ends for speech deepfake detectors primarily focuses on two categories. Hand-crafted filterbank features are transparent but are limited in capturing high-level semantic details, often resulting in performance gaps compared to self-supervised (SSL) features. 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 scatter...

Related in Deepfake Lab