Characterizing The Temporal Dynamics Of Universal Speech Representations For Generalizable Deepfake Detection
2023 · Yi Zhu, Saurabh Powar, Tiago H. Falk
Abstract
Existing deepfake speech detection systems lack generalizability to unseen attacks (i.e., samples generated by generative algorithms not seen during training). Recent studies have explored the use of universal speech representations to tackle this issue and have obtained inspiring results. These works, however, have focused on innovating downstream classifiers while leaving the representation itself untouched. In this study, we argue that characterizing the long-term temporal dynamics of these representations is crucial for generalizability and propose a new method to assess representation dynamics. Indeed, we show that different generative models generate similar representation dynamics patterns with our proposed method. Experiments on the ASVspoof 2019 and 2021 datasets validate the benefits of the proposed method to detect deepfakes from methods unseen during training, significantly improving on several benchmark methods.
Authors
(none)
Tags
Stats
Related papers
- Towards Generalisable And Calibrated Synthetic Speech Detection With Self-supervised Representations (2023)0.00
- Training-free Deepfake Voice Recognition By Leveraging Large-scale Pre-trained Models (2024)9.23
- Anomaly Detection And Localization For Speech Deepfakes Via Feature Pyramid Matching (2025)4.52
- Investigating Self-supervised Representations For Audio-visual Deepfake Detection (2025)0.00
- Combining Automatic Speaker Verification And Prosody Analysis For Synthetic Speech Detection (2022)10.48
- Temporal Variability And Multi-viewed Self-supervised Representations To Tackle The Asvspoof5 Deepfake Challenge (2024)0.00
- Heterogeneity Over Homogeneity: Investigating Multilingual Speech Pre-trained Models For Detecting Audio Deepfake (2024)8.09
- Adversarial Attacks On Audio Deepfake Detection: A Benchmark And Comparative Study (2025)0.00