Semi-supervised Multichannel Speech Separation Based on a Phone-and Speaker-Aware Deep Generative Model of Speech Spectrograms

Mathieu Fontaine

Associate Professor in Machine Listening

After a PhD in Inria Nancy Grand-Est entitled “alpha-stable process for signal processing”, Mathieu Fontaine was a Postdoc from October 2019 to August 2021 at RIKEN Artificial Intelligence Project (AIP) and became a guest at Kyoto University. He is now Associate Professor in Télécom Paris. His interests is mainly on machine listening including, but not limited, to speech enhancement, speaker separation, source localization and music source separation using heavy-tailed probabilistic models and/or deep bayesian networks with also applications in augmented reality.