Home

I am currently Maitre de conférences (~ associate professor) at the Université Paris-Saclay in the Interdisciplinary Laboratory of Numerical Sciences (LISN, formely LIMSI-CNRS) situated in Paris metropolitan area.

My research lies at the intersection of speech processing, computational linguistics, and acoustic phonetics, with a strong focus in prosodic modeling and text-to-speech (TTS) synthesis. Additionally, I develop computational models for dialectology, utilizing acoustic and statistical techniques to model linguistic variation across temporal, regional, and social dimensions.

Prior to my current position, I worked as an electronics and computer science engineer specializing in signal processing. I subsequently conducted my Ph.D. research in speech synthesis at Université Paris-Sud (now Université Paris-Saclay) within the LIMSI-CNRS laboratory. My dissertation, defended in September 2015, investigated expressive speech synthesis.

My research interests span speech/voice processing, auditory perception, and natural language processing (NLP):

• Voice and speech analysis and synthesis, phonetics, prosody
• Digital signal processing, audio, acoustics, spatial hearing
• Natural language processing, machine learning, artificial intelligence