Summary
Nicolas Obin is an Associate Professor at Sorbonne University and a researcher in IRCAM’s Sound Analysis and Synthesis team, specializing in audio signal processing, generative modelling of speech, singing and music, and multimodal sound systems. With a PhD in computer science and an HDR on structured modelling of speech signals, he bridges mathematics, physics, and musicology to explore human–machine and cross-species interaction in sound. He leads teaching and program responsibilities in intelligent systems and deep learning, and founded influential Paris events like DeepVoice and Fast-Forward that connect research, industry and artistic practice. His work emphasizes ethical and cultural questions around AI—digital sovereignty, inclusion of dialects and the impact of generative tools on creative professions—while producing applied outcomes in voice conversion, speech synthesis and cyber-physical musical systems. An active collaborator with artists and festivals, he brings rare fluency across formal modelling, creative production and public engagement.
10 years of coding experience
Master in Arts (MArt) Musicology Arts Aesthetics, Master in Arts (MArt) Musicology Arts Aesthetics at Université Paris 8
Doctor of Philosophy (PhD) Computer Science, Doctor of Philosophy (PhD) Computer Science at Pierre and Marie Curie University
portuguese (a1), French, English