Anis Koubaa

Detecting Voice Conversion Attacks Using Self-Supervised, Handcrafted, and Hybrid Audio Features

Voice conversion attacks are especially challenging to detect because they preserve much of the natural structure of real speech while changing the speaker's identity. In this study, we examine how well handcrafted and self-supervised audio features can detect these attacks, focusing on LFCC and wav2vec 2.0 embeddings,...

Federated few-shot learning with explainable prototype representations for tuberculosis detection in chest X-rays