About
I am Theo Lepage, a Ph.D. student in Machine Learning at Sorbonne University and EPITA Research Laboratory, based in Paris, France. My research focuses on self-supervised learning for producing attack-agnostic representations for speaker and language recognition. Through artificial intelligence, my aim is to enable computers to understand our world.
Read my resume
Send me an email at theo@theolepage.com or reach me on
.
Publications
Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification
INTERSPEECH 2023
Theo Lepage, and Reda Dehak
Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning
INTERSPEECH 2022
Theo Lepage, and Reda Dehak
Projects
sslsv
Framework for training and evaluating self-supervised learning methods for speaker verification.
prophecy
A tiny deep neural network framework developed from scratch in C++ and CUDA.
tensorflood
Tiny automatic differentiation (autodiff) engine for NumPy tensors implemented in Python.