تقرير
Targeted Augmented Data for Audio Deepfake Detection
| العنوان: | Targeted Augmented Data for Audio Deepfake Detection |
|---|---|
| المؤلفون: | Astrid, Marcella, Ghorbel, Enjie, Aouada, Djamila |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Sound, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Audio and Speech Processing |
| الوصف: | The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, which may lead to overfitting, thereby reducing the robustness to unseen manipulations. To enhance the generalization capabilities of audio deepfake detectors, we propose a novel augmentation method for generating audio pseudo-fakes targeting the decision boundary of the model. Inspired by adversarial attacks, we perturb original real data to synthesize pseudo-fakes with ambiguous prediction probabilities. Comprehensive experiments on two well-known architectures demonstrate that the proposed augmentation contributes to improving the generalization capabilities of these architectures. Comment: Accepted in EUSIPCO 2024 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2407.07598 |
| رقم الأكسشن: | edsarx.2407.07598 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |