Biography

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.

Interests

  • Machine listening
  • Machine Learning
  • Probability
  • Augmented Reality

Education

  • PhD in Informatics, 2019

    Lorraine University

  • Master degree in Applied and Fundamental Mathematics, 2015

    Poitiers University

  • BSc in Fundamental Mathematics, 2013

    Rennes I University

Skills

Python

70%

Signal Processing

80%

Mathematics

80%

Experience

 
 
 
 
 

Teacher

Telecom ParisTech

Sep 2018 – Jun 2019 France
Taught optimization for machine learning, introduction to signal processing, ARMA models and NMF
 
 
 
 
 

Mathematic Teacher

Junior High School Alfred de Musset and High School Racan

Jan 2014 – Jun 2015 France

Recent Posts

Projects

Publications

Quickly discover relevant content by filtering publications.

Fast Multichannel Correlated Tensor Factorization for Blind Source Separation

Alpha-Stable Autoregressive Fast Multichannel Nonnegative Matrix Factorization for Joint Speech Enhancement and Dereverberation

PDF DOI

Autoregressive Fast Multichannel Nonnegative Matrix Factorization For Joint Blind Source Separation And Dereverberation

This paper describes a joint blind source separation and dereverberation method that works adaptively and efficiently in a reverberant …
DOI

Fast Multichannel Correlated Tensor Factorization for Blind Source Separation

Neural Full-Rank Spatial Covariance Analysis for Blind Source Separation

This paper describes aneural blind source separation (BSS) method based on amortized variational inference (AVI) of a non-linear …
DOI
See all publications

Popular Topics

"Adaptation models" "Analytical models" "blind dereverberation" "Blind source separation" "Computational modeling" "Decoding" "deep generative models" "joint diagonalization" "multichannel nonnegative matrix factorization" "Neural networks" "Neural source separation" "Noise measurement" "Predictive models" "Probabilistic logic" "Reverberation" "Time-frequency analysis" "Training" "unsupervised training" "variational autoencoders"

Contact