I'm currently Maitre de conférences (~ associate professor) at the Univ. Paris-Saclay and the Laboratoire Interdisciplinaire des Sciences du Numérique (LISN) in Paris metropolitan area (France).
At the LISN, I study machine learning algorithms applied to various digital humanities' tasks, such as natural language processing (e.g., fake news analysis and detection, named entities disambiguation) and speech processing (e.g., speaker diarization, political speech style segmentation).
Prior to my current position, I worked in signal processing as an electronic and computer science engineer. I then gradually switched to machine learning since 2012, when I started my Ph.D. in speech synthesis at the LIMSI-CNRS from the University of Paris-Sud (now Paris-Saclay). Written in French and defended in September 2015, it concerned expressive speech synthesis.
My research interest range from speech and natural language processing (NLP) to auditory spatial perception:
- Speech analysis and synthesis, phonetics, prosody
- Natural language processing, machine learning, deep learning
- Digital signal processing, audio, acoustics, spatial hearing