Thoughts on Anti-Anti-Spoofing
Spoofing Attack Augmentation: Can Differently-Trained Attack Models Improve Generalisation?
Wanying Ge, Xin Wang, Junichi Yamagishi, Massimiliano Todisco, Nicholas Evans
in Proc. ICASSP 2024, pp. 12531-12535.
Comment: Personal favorite.
[Paper]
Malafide: A Novel Adversarial Convolutive Noise Attack Against Deepfake and Spoofing Detection Systems
Michele Panariello*, Wanying Ge*, Hemlata Tak, Massimiliano Todisco, Nicholas Evans (* equal contribution)
in Proc. INTERSPEECH 2023, pp. 2868-2872.
Comment: Named from mala fide (lit. ‘in bad faith’), as opposed to bona fide (lit. ‘in good faith’).
Spoofing-Aware Speaker Verification
Can Spoofing Countermeasure and Speaker Verification Systems Be Jointly Optimised?
Wanying Ge, Hemlata Tak, Massimiliano Todisco, Nicholas Evans
in Proc. ICASSP 2023, pp. 1-5.
Comment: Last time I checked the conference proceeding, all papers are within page 1-5.
On the Potential of Jointly-Optimised Solutions to Spoofing Attack Detection and Automatic Speaker Verification
Wanying Ge*, Hemlata Tak*, Massimiliano Todisco, Nicholas Evans (* equal contribution)
in Proc. IberSPEECH 2022, pp. 51-55.
Comment: Best Paper Award.
Explainability Study - Classifier and Attack Difference
Explainable Deepfake and Spoofing Detection: An Attack Analysis Using SHapley Additive exPlanations
Wanying Ge, Massimiliano Todisco, Nicholas Evans
in Proc. The Speaker and Language Recognition Workshop (Odyssey 2022), pp. 70-76.
Explaining Deep Learning Models for Spoofing and Deepfake Detection With SHapley Additive exPlanations
Wanying Ge, Jose Patino, Massimiliano Todisco, Nicholas Evans
in Proc. ICASSP 2022, pp. 6387-6391.
[Paper]
Neural Architecture Search for Voice Anti-Spoofing
Raw Differentiable Architecture Search for Speech Deepfake and Spoofing Detection
Wanying Ge, Jose Patino, Massimiliano Todisco, Nicholas Evans
in Proc. 2021 Edition of the Automatic Speaker Verification and Spoofing Countermeasures Challenge (ASVspoof 2021 Workshop), pp. 22-28.
Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detection
Wanying Ge, Michele Panariello, Jose Patino, Massimiliano Todisco, Nicholas Evans
in Proc. INTERSPEECH 2021, pp. 4319-4323.
Speech Separation
Monaural Noisy Speech Separation Combining Sparse Non-negative Matrix Factorization and Deep Attractor Network
Wanying Ge, Tianqi Zhang, Congcong Fan, Tian Zhang
Chinese Journal of Acoustics, 2020