mlsanityData to 14 Oct 2026

Supervised Post-training of Speech Foundation Models for Robust Adaptation in Speech Deepfake Detection

arXiv 2606.25328 ↗First posted 24 Jun 2026cs.SD cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large speech foundation models have shown strong potential for speech deepfake detection, but direct fine-tuning is limited by a mismatch between self-supervised pre-training objectives and spoof-specific artifacts. To address this, we propose a mix-frame post-training strategy to create localized spoof-oriented perturbations and use frame-level supervision to encourage the SSL model to learn local inconsistencies that are critical for robust spoof detection. On ASVspoof5, we achieve state-of-the-art EER 4.50% for a single model without data augmentation. On ASVspoof2021 LA/DF, it further achieves only 0.16% absolute EER gap between LA and DF, indicating strong and balanced robustness across distinct distortion conditions. These results show that supervised post-training provides an effective and practical way to adapt speech foundation models for robust deepfake detection.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 31 references that are in the map. First posted on arXiv 24 Jun 2026.

Builds on

23 of 31 references.

References · 23

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  3. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  4. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  5. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 628
  6. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 180
  7. 2022ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wildcited by 121
  8. 2024ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scalecited by 91
  9. 2021ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speechcited by 58
  10. 2022The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterancecited by 47
  11. 2021Investigating self-supervised front ends for speech spoofing countermeasurescited by 46
  12. 2022The Vicomtech Audio Deepfake Detection System based on Wav2Vec2 for the 2022 ADD Challengecited by 35
11 more
  1. 2023Audio Deepfake Detection with Self-Supervised WavLM and Multi-Fusion Attentive Classifiercited by 27
  2. 2025Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofingcited by 19
  3. 2024Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detectioncited by 17
  4. 2024BUT Systems and Analyses for the ASVspoof 5 Challengecited by 12
  5. 2024Enhancing Partially Spoofed Audio Localization with Boundary-aware Attention Mechanismcited by 9
  6. 2022Anti-Spoofing Using Transfer Learning with Variational Information Bottleneckcited by 8
  7. 2024Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CtrSVDD) Challenge 2024cited by 7
  8. 2024Towards Quantifying and Reducing Language Mismatch Effects in Cross-Lingual Speech Anti-Spoofingcited by 7
  9. 2024Learn from Real: Reality Defender's Submission to ASVspoof5 Challengecited by 6
  10. 2024SZU-AFS Antispoofing System for the ASVspoof 5 Challengecited by 5
  11. 2025MoLEx: Mixture of LoRA Experts in Speech Self-Supervised Models for Audio Deepfake Detectioncited by 5

Built on by

Not cited yet.