mlsanityData to 14 Oct 2026

AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks

arXiv 2110.01200 ↗First posted 4 Oct 2021eess.AS cs.AI cs.LGcited by 180

Not on the map. Why?

Abstract (arXiv)

Artefacts that differentiate spoofed from bona-fide utterances can reside in spectral or temporal domains. Their reliable detection usually depends upon computationally demanding ensemble systems where each subsystem is tuned to some specific artefacts. We seek to develop an efficient, single system that can detect a broad range of different spoofing attacks without score-level ensembles. We propose a novel heterogeneous stacking graph attention layer which models artefacts spanning heterogeneous temporal and spectral domains with a heterogeneous attention mechanism and a stack node. With a new max graph operation that involves a competitive mechanism and an extended readout scheme, our approach, named AASIST, outperforms the current state-of-the-art by 20% relative. Even a lightweight variant, AASIST-L, with only 85K parameters, outperforms all competing systems.

Key facts. Cited by 180 papers in the map (data through 14 Oct 2026). Builds on 30 of its 42 references that are in the map. First posted on arXiv 4 Oct 2021.

Builds on

30 of 42 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2017Graph Attention Networkscited by 8,923
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  6. 2019Heterogeneous Graph Attention Networkcited by 734
  7. 2017Self-Normalizing Neural Networkscited by 598
  8. 2019Graph U-Netscited by 492
  9. 2019Self-Attention Graph Poolingcited by 421
  10. 2017Population Based Training of Neural Networkscited by 367
  11. 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 178
  12. 2018Speaker Recognition from Raw Waveform with SincNetcited by 166
18 more
  1. 2020End-to-end anti-spoofing with RawNet2cited by 164
  2. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 161
  3. 2015A Light CNN for Deep Face Representation with Noisy Labelscited by 126
  4. 2021End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detectioncited by 70
  5. 2020One-class Learning Towards Synthetic Voice Spoofing Detectioncited by 61
  6. 2021A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detectioncited by 56
  7. 2020Replay and Synthetic Speech Detection with Res2net Architecturecited by 39
  8. 2021Towards End-to-End Synthetic Speech Detectioncited by 38
  9. 2021Raw Differentiable Architecture Search for Speech Deepfake and Spoofing Detectioncited by 22
  10. 2018t-DCF: a Detection Cost Function for the Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verificationcited by 19
  11. 2021Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attackscited by 18
  12. 2021Graph Attention Networks for Anti-Spoofingcited by 17
  13. 2020An explainability study of the constant Q cepstral coefficient spoofing countermeasure for automatic speaker verificationcited by 13
  14. 2020Spoofing Attack Detection using the Non-linear Fusion of Sub-band Classifierscited by 9
  15. 2021Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detectioncited by 9
  16. 2020Integrated Replay Spoofing-aware Text-independent Speaker Verificationcited by 6
  17. 2020Graph Attention Networks for Speaker Verificationcited by 6
  18. 2019Replay attack detection with complementary high-resolution information using end-to-end DNN for the ASVspoof 2019 Challengecited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 8; 2023: 13; 2024: 50; 2025: 42; 2026: 66.

180 papers.

Sort:

By area:

  1. 2024ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scalecited by 91
  2. 2025Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024cited by 45
  3. 2024The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audiocited by 31
  4. 2024XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detectioncited by 30
  5. 2023Improved DeepFake Detection Using Whisper Featurescited by 29
  6. 2024Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detectioncited by 25
  7. 2024ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf modelscited by 22
  8. 2024SpoofCeleb: Speech Deepfake Detection and SASV In The Wildcited by 22
  9. 2023SingFake: Singing Voice Deepfake Detectioncited by 21
  10. 2024SONICS: Synthetic Or Not -- Identifying Counterfeit Songscited by 21
  11. 2025Speech DF Arena: A Leaderboard for Speech DeepFake Detection Modelscited by 21
  12. 2024DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Datasetcited by 20
38 more
  1. 2024Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0cited by 20
  2. 2025Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofingcited by 19
  3. 2022SAMO: Speaker Attractor Multi-Center One-Class Learning for Voice Anti-Spoofingcited by 18
  4. 2025ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detectioncited by 17
  5. 2025SpeechJudge: Towards Human-Level Judgment for Speech Naturalnesscited by 15
  6. 2023Learning From Yourself: A Self-Distillation Method for Fake Speech Detectioncited by 13
  7. 2023One-Class Knowledge Distillation for Spoofing Speech Detectioncited by 13
  8. 2023FSD: An Initial Chinese Dataset for Fake Song Detectioncited by 12
  9. 2025EnvSDD: Benchmarking Environmental Sound Deepfake Detectioncited by 11
  10. 2023Malafide: a novel adversarial convolutive noise attack against deepfake and spoofing detection systemscited by 10
  11. 2024How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio?cited by 10
  12. 2024Exploring WavLM Back-ends for Speech Spoofing and Deepfake Detectioncited by 10
  13. 2024Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlookcited by 10
  14. 2025BiCrossMamba-ST: Speech Deepfake Detection with Bidirectional Mamba Spectro-Temporal Cross-Attentioncited by 10
  15. 2023Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofingcited by 9
  16. 2024FairSSD: Understanding Bias in Synthetic Speech Detectorscited by 9
  17. 2024CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learningcited by 9
  18. 2024Harder or Different? Understanding Generalization of Audio Deepfake Detectioncited by 9
  19. 2024AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challengecited by 9
  20. 2022Anti-Spoofing Using Transfer Learning with Variational Information Bottleneckcited by 8
  21. 2023HM-Conformer: A Conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methodscited by 8
  22. 2024SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detectioncited by 8
  23. 2024USTC-KXDIGIT System Description for ASVspoof5 Challengecited by 8
  24. 2021Multi-scale speaker embedding-based graph attention networks for speaker diarisationcited by 7
  25. 2023Towards single integrated spoofing-aware speaker verification embeddingscited by 7
  26. 2024Retrieval-Augmented Audio Deepfake Detectioncited by 7
  27. 2024Detecting Audio-Visual Deepfakes with Fine-Grained Inconsistenciescited by 7
  28. 2024Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CtrSVDD) Challenge 2024cited by 7
  29. 2024Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofingcited by 7
  30. 2024Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Datasetcited by 7
  31. 2025Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perceptioncited by 7
  32. 2025Multilingual Source Tracing of Speech Deepfakes: A First Benchmarkcited by 7
  33. 2023How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learningcited by 6
  34. 2024a-DCF: an architecture agnostic metric with application to spoofing-robust speaker verificationcited by 6
  35. 2024Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audiocited by 6
  36. 2024The DeepSpeak Datasetcited by 6
  37. 2024Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein modelcited by 6
  38. 2024Learn from Real: Reality Defender's Submission to ASVspoof5 Challengecited by 6

50 most cited of 180 All 180 (JSON)