mlsanityData to 7 Oct 2026

Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0

arXiv 2409.11909 ↗First posted 18 Sep 2024cs.SD eess.AScited by 20

On the map: Mixture-of-experts → Multimodal MoE models

Abstract (arXiv)

Speech synthesis technology has posed a serious threat to speaker verification systems. Currently, the most effective fake audio detection methods utilize pretrained models, and integrating features from various layers of pretrained model further enhances detection performance. However, most of the previously proposed fusion methods require fine-tuning the pretrained models, resulting in excessively long training times and hindering model iteration when facing new speech synthesis technology. To address this issue, this paper proposes a feature fusion method based on the Mixture of Experts, which extracts and integrates features relevant to fake audio detection from layer features, guided by a gating network based on the last layer feature, while freezing the pretrained model. Experiments conducted on the ASVspoof2019 and ASVspoof2021 datasets demonstrate that the proposed method achieves competitive performance compared to those requiring fine-tuning.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in Multimodal MoE models, one of 12 directions in Mixture-of-experts. Builds on 25 of its 34 references that are in the map. First posted on arXiv 18 Sep 2024.

Builds on

25 of 34 references.

References · 25

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  2. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  3. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  4. 2022Masked Autoencoders that Listencited by 271
  5. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 173
  6. 2020End-to-end anti-spoofing with RawNet2cited by 160
  7. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 157
  8. 2022Does Audio Deepfake Detection Generalize?cited by 129
  9. 2022ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wildcited by 118
  10. 2022Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentationcited by 110
  11. 2021RawBoost: A Raw Data Boosting and Augmentation Method applied to Automatic Speaker Verification Anti-Spoofingcited by 64
  12. 2023Multi-modal Gated Mixture of Local-to-Global Experts for Dynamic Image Fusioncited by 54
13 more
  1. 2023Audio Deepfake Detection: A Surveycited by 49
  2. 2021Investigating self-supervised front ends for speech spoofing countermeasurescited by 43
  3. 2021Towards End-to-End Synthetic Speech Detectioncited by 37
  4. 2022The Vicomtech Audio Deepfake Detection System based on Wav2Vec2 for the 2022 ADD Challengecited by 33
  5. 2024The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audiocited by 31
  6. 2023Audio Deepfake Detection with Self-Supervised WavLM and Multi-Fusion Attentive Classifiercited by 26
  7. 2024Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detectioncited by 17
  8. 2023Improving Short Utterance Anti-Spoofing with AASIST2cited by 11
  9. 2023One-Class Knowledge Distillation for Spoofing Speech Detectioncited by 11
  10. 2023Learning From Yourself: A Self-Distillation Method for Fake Speech Detectioncited by 9
  11. 2024Generalized Fake Audio Detection via Deep Stable Learningcited by 5
  12. 2024Genuine-Focused Learning using Mask AutoEncoder for Generalized Fake Audio Detectioncited by 5
  13. 2023Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detectioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 9; 2026: 10.

20 papers.

Sort:

By area:

  1. 2024XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detectioncited by 27
  2. 2025Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofingcited by 17
  3. 2025Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perceptioncited by 7
  4. 2026AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plancited by 3
  5. 2025Attention-based Mixture of Experts for Robust Speech Deepfake Detectioncited by 2
  6. 2025Addressing Gradient Misalignment in Data-Augmented Training for Robust Speech Deepfake Detectioncited by 2
  7. 2025Fake Speech Wild: Detecting Deepfake Speech on Social Media Platformcited by 1
  8. 2025MoTAS: MoE-Guided Feature Selection from TTS-Augmented Speech for Enhanced Multimodal Alzheimer's Early Screeningcited by 1
  9. 2025Generalizable Speech Deepfake Detection via Information Bottleneck Enhanced Adversarial Alignmentcited by 1
  10. 2025SONAR: Spectral-Contrastive Audio Residuals for Generalizable Deepfake Detectioncited by 1
  11. 2026Teffic-Audio: Tell Fact from Fictioncited by 1
  12. 2025HuLA: Prosody-Aware Anti-Spoofing with Multi-Task Learning for Expressive and Emotional Synthetic Speechcited by 0
8 more
  1. 2026DFKI-Speech System for WildSpoof Challenge: A robust framework for SASV In-the-Wildcited by 0
  2. 2026HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detectioncited by 0
  3. 2026Deepfake Audio Detection Using Self-supervised Fusion Representationscited by 0
  4. 2026From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofingcited by 0
  5. 2026Audio-Anchored Fusion of Multi-Ratio DiT Reconstruction Residuals for Cross-Domain Audio Deepfake Detectioncited by 0
  6. 2026CRAF: Cross-View Residual-Aware Fusion for Deepfake Speech Detectioncited by 0
  7. 2026What Survives the Codec Shift: Pooled No-Vocals Residuals for Speech Deepfake Detectioncited by 0
  8. 2026Domain-Adaptive Dual-Gating Mixture of Experts for Generalizable Speech Deepfake Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Wav2DF-TSL: Two-stage Learning with Efficient Pre-training and Hierarchical Experts Fusion for Robust Audio Deepfake Detection
  2. 2024Leveraging Mixture of Experts for Improved Speech Deepfake Detection
  3. 2025Noise-Conditioned Mixture-of-Experts Framework for Robust Speaker Verification
  4. 2026Component-Level Ensemble Fusion for Speech and Environmental Sound Deepfake Detection ↗
  5. 2025Benchmarking Fake Voice Detection in the Fake Voice Generation Arms Race ↗
  6. 2019MoEVC: A Mixture-of-experts Voice Conversion System with Sparse Gating Mechanism for Accelerating Online Computation
  7. 2025Mixture of Low-Rank Adapter Experts in Generalizable Audio Deepfake Detection
  8. 2023Diffusion-Based Adversarial Purification for Speaker Verification