← Back to all news
arXiv Computation and Language By Xi Xuan, Davide Carbone, Wenxin Zhang, Tomi H. Kinnunen

WaveScat: Wavelet Scattering Front-Ends with Self-Supervised Features for Speech Deepfake Detection

Read the original on arXiv Computation and Language →

WaveScat introduces a new family of feature extractors for speech deepfake detection that merges wavelet scattering transform (WST) with self‑supervised learning. By cascading wavelet convolutions with modulus nonlinearities, WaveScat produces deformation‑stable, multi‑scale features that capture both low‑level spectral details and higher‑level information. Experiments on Deepfake‑Eval‑2024 and cross‑dataset tests (SpoofCeleb, In‑the‑Wild, ASVspoof 5) demonstrate that WaveScat significantly outperforms existing front‑ends, with a small averaging scale and high‑frequency directional resolution proving crucial for detecting subtle artifacts.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Sep 25

WST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection

The paper introduces WST-Graph, a topology-preserving wavelet scattering front-end designed for speech deepfake detection. It reconstructs wavelet scattering paths into a sparse modulation‑carrier grid that feeds an AASIST graph backend, employing modulation‑level normalization and adaptive local attention pooling to produce fixed relative‑time representations while keeping acoustic axes intact. The resulting waveform‑to‑graph interface uses about 60% fewer trainable parameters than AASIST yet remains competitive, showing clear improvements on selected out‑of‑domain benchmarks.

By Kwok-Ho Ng, Tingting Song, Bingwen Feng, Zhihua Xia
benchmarks
More like this →
arXiv AI
Sep 10

AudioFuse: Unified Spectral-Temporal Learning via a Hybrid ViT-1D CNN Architecture for Robust Phonocardiogram Classification

AudioFuse is a hybrid architecture that jointly learns from spectrograms and raw waveforms to classify phonocardiograms. It combines a wide-and-shallow Vision Transformer for spectral features with a shallow 1D CNN for temporal waveforms, reducing overfitting while capturing complementary information. On the PhysioNet 2016 dataset, AudioFuse achieves a state‑of‑the‑art ROC‑AUC of 0.8608 and shows superior robustness to domain shift on the PASCAL dataset, outperforming both spectrogram‑only and waveform‑only baselines.

By Md. Saiful Bari Siddiqui, Utsab Saha
llmscomputer-visionbenchmarkssafety
More like this →