Hi! I am a Ph.D candidate at Université Paris Cité (Paris, France), advised by Prof. Guillaume Wisniewski. My research focuses on the analysis and interpretation of representations learned by speech foundation models. I aim to better understand what these models learn from large-scale speech data and how linguistic information emerges within their representations.

More broadly, I am interested in developing data-efficient approaches for low-resource languages. I work toward methods that can support field linguists in transcription and documentation, helping improve the inclusivity of speech technologies.

Keywords: Speech Foundation Models, Self-Supervised Learning, Speech Model Interpretability, Low-Resource Languages, Automatic Speech Recognition, Computational Linguistics.

News

• July 2026 — I attended the 16th Lisbon Machine Learning Summer School (LxMLS 2026) at Instituto Superior Técnico in Lisbon, Portugal.
• June 2026 — Our paper L’accent comme structure géométrique persistante dans les représentations de la parole, with Guillaume Wisniewski, was accepted at CORIA-TALN 2026.
• April 2026 — Our preprint Target Parameterization in Diffusion Models for Nonlinear Spatiotemporal System Identification, with Achraf El Messaoudi and Karim Cherifi, is now available on arXiv.