supervision

PhD students

Period Name Project Co-supervisor
2024-2027 Guilhem Fauré End-to-end Speech-to-Sign Language Generation Slim Ouni
2023-2026 Jean-Eudes Ayilo Audio-visual Speech Enhancement: Bridging the Gap between Supervised & Unsupervised Approaches Romain Serizel
2021-2024 Can Cui End-to-end Automatic Speech Recognition for Meetings Transcription Emmanuel Vincent

Masters (M2) students

Year Name University Project Co-supervisor Afterwards Career
2023 Louis Lalay Sorbonne University (ATIAM) Dictionary Learning for Deep Unsupervised Speech Separation Paul Magron PhD student
2023 Jean-Eudes Ayilo Aix-Marseille University Audio-Visual Speech Enhancement based on Diffusion Models Romain Serizel PhD student
2023 Berné Nortier Paris Dauphine University Unsupervised Speech Enhancement with Diffusion-based Generative Models Romain Serizel PhD student
2023 Antoine Bruez École des Mines d'Alès Efficient Attention-based Fusion Mechanisms for Audio-Visual Speech Enhancement Romain Serizel --
2022 Ali Golmakani Université Paris-Saclay Unsupervised Audio-Visual Speech Enhancement using Dynamical Generative Models Romain Serizel --
2021 Ali Rida Sahili ENS Paris-Saclay (MVA) Disentanglement of Latent Codes in Variational Auto-encoders Xavier Alameda-Pineda R&D CV engineer
2020 Viet Nhat Nguyen University of Trento Audio-visual Speech Separation using Variational Auto-encoders Xavier Alameda-Pineda ML engineer

Masters (M1) students

Year Name University Project Afterwards Career
2022 Valentin Gerard ENS des Mines de Nancy VAE-based Audio-visual Speech Generative Modeling M2 (MVA) at ENS Paris-Saclay