Temporal Variability And Multi-viewed Self-supervised Representations To Tackle The Asvspoof5 Deepfake Challenge
2024 · Yuankun Xie, Xiaopeng Wang, Zhiyong Wang, et al.
Abstract
ASVspoof5, the fifth edition of the ASVspoof series, is one of the largest global audio security challenges. It aims to advance the development of countermeasure (CM) to discriminate bonafide and spoofed speech utterances. In this paper, we focus on addressing the problem of open-domain audio deepfake detection, which corresponds directly to the ASVspoof5 Track1 open condition. At first, we comprehensively investigate various CM on ASVspoof5, including data expansion, data augmentation, and self-supervised learning (SSL) features. Due to the high-frequency gaps characteristic of the ASVspoof5 dataset, we introduce Frequency Mask, a data augmentation method that masks specific frequency bands to improve CM robustness. Combining various scale of temporal information with multiple SSL features, our experiments achieved a minDCF of 0.0158 and an EER of 0.55% on the ASVspoof 5 Track 1 evaluation progress set.
Authors
(none)
Tags
Stats
Related papers
- Asasvicomtech: The Vicomtech-ugr Speech Deepfake Detection And SASV Systems For The Asvspoof5 Challenge (2024)5.24
- Automatic Speaker Verification Spoofing And Deepfake Detection Using Wav2vec 2.0 And Data Augmentation (2022)17.35
- Asvspoof 5: Design, Collection And Validation Of Resources For Spoofing, Deepfake, And Adversarial Attack Detection Using Crowdsourced Speech (2025)9.76
- Exploring Wavlm Back-ends For Speech Spoofing And Deepfake Detection (2024)4.52
- Asvspoof 2021: Towards Spoofed And Deepfake Speech Detection In The Wild (2022)17.95
- Securing Voice Biometrics: One-shot Learning Approach For Audio Deepfake Detection (2023)9.03
- Investigating Self-supervised Representations For Audio-visual Deepfake Detection (2025)0.00
- AASIST3: Kan-enhanced AASIST Speech Deepfake Detection Using SSL Features And Additional Regularization For The Asvspoof 2024 Challenge (2024)9.03