4 papers
Adaptive Regularization for Sparsity Control in Bregman-Based Optimizers
Ahmad Aloradi, Tim Roith, Emanuël A. P. Habets +1
Sparse training reduces the memory and computational costs of deep neural networks. However, sparse optimization methods, e.g., those adding an penalty, often control spar…
VoxATtack: A Multimodal Attack on Voice Anonymization Systems
Ahmad Aloradi, Ünal Ege Gaznepoglu, Emanuël A. P. Habets +1
Voice anonymization systems aim to protect speaker privacy by obscuring vocal traits while preserving the linguistic content relevant for downstream applications. However, because…
You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attacks
Ünal Ege Gaznepoglu, Anna Leschanowsky, Ahmad Aloradi +4
Speaker anonymization systems hide the identity of speakers while preserving other information such as linguistic content and emotions. To evaluate their privacy benefits, attacks…
Speaker Verification in Multi-Speaker Environments Using Temporal Feature Fusion
Ahmad Aloradi, Wolfgang Mack, Mohamed Elminshawi +1
Verifying the identity of a speaker is crucial in modern human-machine interfaces, e.g., to ensure privacy protection or to enable biometric authentication. Classical speaker verif…