Accéder directement au contenu

Marc Tommasi

5
Documents

Présentation

Professor in Computer Science at [Lille university](https://www.univ-lille.fr/). I am a member of [CRIStAL](https://www.cristal.univ-lille.fr/?rubrique9) lab. I am the leader of the [Magnet Team](https://team.inria.fr/magnet). My research interests are machine learning, structured prediction for trees and graphs. I have also studied tree automata and set constraints.

Publications

yannick-esteve
Image document

Extraction d'informations liées au locuteur depuis un modèle acoustique personnalisé

 Salima Mdhaffar , Jean-François A Bonastre , Marc Tommasi , Natalia Tomashenko , Yannick Estève
JEP 2022, Jun 2022, île de Noirmoutier, France
Communication dans un congrès hal-03706944v1
Image document

Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition

 Salima Mdhaffar , Jean-François Bonastre , Marc Tommasi , Natalia Tomashenko , Yannick Estève
IEEE ICASSP 2022, 2022, Singapour, Singapore
Communication dans un congrès hal-03539741v1
Image document

On speaker verification from the neural network footprint of personalized acoustic models

 Natalia Tomashenko , Salima Mdhaffar , Marc Tommasi , Yannick Estève , Jean-François Bonastre
Journées d'Études sur la Parole - JEP2022, Jun 2022, Île de Noirmoutier, France
Communication dans un congrès hal-03626964v1
Image document

Privacy attacks for automatic speech recognition acoustic models in a federated learning framework

 Natalia Tomashenko , Salima Mdhaffar , Marc Tommasi , Yannick Estève , Jean-François Bonastre
ICASSP 2022, 2022, Singapour, Singapore
Communication dans un congrès hal-03539742v2
Image document

Study on Acoustic Model Personalization in a Context of Collaborative Learning Constrained by Privacy Preservation

 Salima Mdhaffar , Marc Tommasi , Yannick Estève
SPECOM 2021 - 23rd International Conference on Speech and Computer, Sep 2021, St Petersburg, Russia. pp.426 - 436, ⟨10.1007/978-3-030-87802-3_39⟩
Communication dans un congrès hal-03369206v1