Teaching activities

Vocational training - From machine learning to deep learning - Grenoble-INP (2 days)

* See here for more information


Automatic speech processing  - PHELMA (Grenoble-INP)

    • Lecture 16h + Lab work (4h), more information here, (slides available on Chamilo) 

Introduction to deep learning - PHELMA (Grenoble-INP)

* Lectures (2h): ConvNet, RNN (jupiter notebook available on Chamilo)


Fundamentals of Probabilistic Graphical Models - Master 2 MOSIG-SIAM (UGA)

* Lecture (2x1h30): Hidden Markov models

* Lab work (1h30): Practical application of an HMM-based acoustic-phonetic decoder (slides available on Chamilo)


Bayesian methods for data image analysis - Master 2 SIGMA (UGA)

  • Lecture (2x2h): Gaussian Mixture models, Hidden-Markov model, application to automatic speech recognition (slides here)


Real-time audio signal processing - PHELMA (Grenoble-INP)

* Lectures (2x2h) : (slides here)

* Lab work (4*4h) : implementation of a real-time convolution reverb (audio effect) (sujet ici) / (ressources ici)

Grenoble Images Parole Signal Automatique laboratoire

UMR 5216 CNRS - Grenoble INP - Université Joseph Fourier - Université Stendhal