mlsanityData to 14 Oct 2026

SpAArSIST: Sparsified AASIST for Efficient and Reliable Anti-Spoofing

arXiv 2606.11674 ↗First posted 10 Jun 2026cs.SD cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We present SpAArSIST, a deployment-oriented refinement of the widely used AASIST graph pooling backend for self-supervised learning (SSL) based anti-spoofing. Motivated by redundant operations in public implementations, we replace learned pooling and stack-node attention with explicit, lightweight choices: separate train and inference graph pooling ratios (ktr,kinf), magnitude-based node scoring, and mean aggregation of graph nodes. The best overall configuration (rank 1) cuts backend compute by 20.7% (195.045M rightarrow 154.706M MACs) and model size by 4.1% (611.8k rightarrow 586.4k params), while improving out-of-domain robustness on In-the-Wild to 2.82% EER and 0.078 minDCF (from 4.64% and 0.133) and remaining competitive on ASVspoof5. We further provide a composite selection score that summarizes accuracy, calibration, and compute to support balanced deployment-oriented model choice.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 26 references that are in the map. First posted on arXiv 10 Jun 2026.

Builds on

16 of 26 references.

References · 16

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  2. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  3. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
  4. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 180
  5. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 161
  6. 2022Does Audio Deepfake Detection Generalize?cited by 135
  7. 2022Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentationcited by 117
  8. 2024ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scalecited by 91
  9. 2021RawBoost: A Raw Data Boosting and Augmentation Method applied to Automatic Speaker Verification Anti-Spoofingcited by 67
  10. 2023ADD 2023: the Second Audio Deepfake Detection Challengecited by 64
  11. 2025ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speechcited by 26
  12. 2022An attention-based backend allowing efficient fine-tuning of transformer models for speaker verificationcited by 16
4 more
  1. 2024BUT Systems and Analyses for the ASVspoof 5 Challengecited by 12
  2. 2024AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challengecited by 9
  3. 2024CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verificationcited by 5
  4. 2025Towards Scalable AASIST: Refining Graph Attention for Speech Deepfake Detectioncited by 1

Built on by

Not cited yet.