I'm Theo Lepage. I hold a Ph.D. in Artificial Intelligence from 
Sorbonne University and my research focuses on AI/ML for Speech, notably speaker recognition and speech anti-spoofing, with a broader interest in self-supervised learning. Through my work, I aim to develop technologies capable of understanding and interpreting all aspects of human conversations.
Experience
Proposed self-supervised methods for speaker recognition • Published 8 papers at leading speech venues (Interspeech, IEEE TASLP) • DINO-WavLM → SOTA performance on VoxCeleb (1.06% EER on Vox1-O) • SSPS → latent-space positive sampling (-58% EER for SimCLR) • sslsv → open-source PyTorch toolkit for self-supervised speaker verification
Developed deep learning models (CNN with self-attention) for end-to-end MR image enhancement (denoising & super-resolution)
Education
Thesis: Self-Supervised Learning for Speaker Recognition • Supervised by Reda Dehak @ LRE-EPITA • Learn more at /phd_thesis →
AI/ML for Computer Vision • Research student @ LRDE (IS2022) • Teaching assistant (C & Unix) • Exchange semester at CSUMB
Publications
