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

arXiv: https://arxiv.org/abs/2609.29372 · HTML: https://mlsanity.com/paper/2609.29372/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 20 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks](https://mlsanity.com/paper/2110.01200/) (2021)
- [Speaker Recognition from Raw Waveform with SincNet](https://mlsanity.com/paper/1808.00158/) (2018)
- [End-to-end anti-spoofing with RawNet2](https://mlsanity.com/paper/2011.01108/) (2020)
- [ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection](https://mlsanity.com/paper/2109.00537/) (2021)
- [Does Audio Deepfake Detection Generalize?](https://mlsanity.com/paper/2203.16263/) (2022)
- [Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation](https://mlsanity.com/paper/2202.12233/) (2022)
- [ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale](https://mlsanity.com/paper/2408.08739/) (2024)
- [Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward](https://mlsanity.com/paper/2103.00484/) (2021)
- [Kymatio: Scattering Transforms in Python](https://mlsanity.com/paper/1812.11214/) (2018)
- [ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech](https://mlsanity.com/paper/2102.05889/) (2021)
- [Deep Scattering Spectrum](https://mlsanity.com/paper/1304.6763/) (2013)
- [Audio Deepfake Detection: A Survey](https://mlsanity.com/paper/2308.14970/) (2023)
- [MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder](https://mlsanity.com/paper/2505.07916/) (2025)
- [Speech DF Arena: A Leaderboard for Speech DeepFake Detection Models](https://mlsanity.com/paper/2509.02859/) (2025)
- [Joint Time-Frequency Scattering for Audio Classification](https://mlsanity.com/paper/1512.02125/) (2015)
- [Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm](https://mlsanity.com/paper/2607.23938/) (2026)
- [dots.tts Technical Report](https://mlsanity.com/paper/2606.07080/) (2026)
- [WaveScat: Wavelet Scattering Front-Ends with Self-Supervised Features for Speech Deepfake Detection](https://mlsanity.com/paper/2602.02980/) (2026)

## Abstract (arXiv)

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 https://github.com/saki-ciallo/wst-graph.