Simon Leglaive
Assistant Professor
CentraleSupélec, IETR (UMR CNRS 6164)
simon.leglaive@centralesupelec.fr
+33 (0)2 99 84 45 82
CentraleSupélec - Rennes Campus
Avenue de la Boulaie
CS 47601
F-35576 Cesson-Sévigné Cedex
Google Scholar
Twitter
Preprints
|
MEGA: Masked generative autoencoder for human mesh recovery
Guénolé Fiche, Simon Leglaive, Xavier Alameda-Pineda, Francesc Moreno-Noguer arXiv preprint arXiv:2405.18839, 2024 Paper | Webpage |
|
|
A vector quantized masked autoencoder for audiovisual speech emotion recognition Samir Sadok, Simon Leglaive, Renaud Séguier arXiv preprint arXiv:2305.03568, 2024 Paper | Demo |
|
|
HiT-DVAE: Human motion generation via hierarchical transformer dynamical VAE Xiaoyu Bie, Wen Guo, Simon Leglaive, Laurent Girin, Francesc Moreno-Noguer, Xavier Alameda-Pineda arXiv preprint arXiv:2204.01565, 2022 Paper |
Journals
| 2025 |
Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge Simon Leglaive, Matthieu Fraticelli, Hend ElGhazaly, Léonie Borne, Mostafa Sadeghi, Scott Wisdom, Manuel Pariente, John R. Hershey, Daniel Pressnitzer, Jon P. Barker Computer Speech & Language, vol. 89, 2025 Paper | GitHub | Data |
| 2024 |
A multimodal dynamical variational autoencoder for audiovisual speech representation learning Samir Sadok, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda, Renaud Séguier Neural Networks, 2024 Paper | Demo |
| 2023 |
Learning and controlling the source-filter representation of speech with a variational autoencoder Samir Sadok, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda, Renaud Séguier Speech Communication, vol. 148, 2023 Paper | Demo | Code |
| 2022 |
Unsupervised speech enhancement using dynamical variational autoencoders Xiaoyu Bie, Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 30, 2022 Paper | Demo | Code |
| 2021 |
Dynamical variational autoencoders: A comprehensive review Laurent Girin, Simon Leglaive, Xiaoyu Bie, Julien Diard, Thomas Hueber, Xavier Alameda-Pineda Foundations and Trends in Machine Learning, vol. 15, no. 1-2, 2021 Paper | Code |
| 2020 |
Audio-visual speech enhancement using conditional variational auto-encoders Mostafa Sadeghi, Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin, Radu Horaud IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 28, 2020 Paper | Code |
| 2019 |
Noise power spectral density estimation using long short-term memory Xiaofei Li, Simon Leglaive, Laurent Girin, Radu Horaud IEEE Signal Processing Letters, vol. 26, no. 6, 2019 Paper |
| 2018 |
Student's t source and mixing models for multichannel audio source separation
Simon Leglaive, Roland Badeau, Gaël Richard IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 26, no. 6, 2018 Paper | Demo | Code |
| 2016 |
Multichannel audio source separation with probabilistic reverberation priors Simon Leglaive, Roland Badeau, Gaël Richard IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 24, no. 12, 2016 Paper | Demo | Code |
International conferences
| 2024 |
VQ-HPS: Human pose and shape estimation in a vector-quantized latent space
Guénolé Fiche, Simon Leglaive, Xavier Alameda-Pineda, Antonio Agudo, Francesc Moreno-Noguer Accepted at European Conference on Computer Vision (ECCV), Milano, Italy, 2024 Paper | Webpage |
|
Towards improving speech emotion recognition using synthetic data augmentation from emotion conversion Karim M. Ibrahim, Antony Perzo, Simon Leglaive IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Seoul, Korea, 2024 Paper |
|
| 2023 |
Motion-DVAE: Unsupervised learning for fast human motion denoising Guénolé Fiche, Simon Leglaive, Xavier Alameda-Pineda, Renaud Séguier ACM SIGGRAPH Conference on Motion, Interaction and Games (ACM MIG), 2023 Paper | Webpage |
|
SwimXYZ: A large-scale dataset of synthetic swimming motions and videos Guénolé Fiche, Vincent Sevestre, Camila Gonzalez-Barral, Simon Leglaive, Renaud Séguier ACM SIGGRAPH Conference on Motion, Interaction and Games (ACM MIG), 2023 Paper | Webpage |
|
|
The CHiME-7 UDASE task: Unsupervised domain adaptation for conversational speech enhancement Simon Leglaive, Léonie Borne, Efthymios Tzinis, Mostafa Sadeghi, Matthieu Fraticelli, Scott Wisdom, Manuel Pariente, Daniel Pressnitzer, John R. Hershey The 7th International Workshop on Speech Processing in Everyday Environments (CHiME), Dublin, Ireland, 2023 Paper | Website | Slides |
|
|
Unsupervised speech enhancement with deep dynamical generative speech and noise models Xiaoyu Lin, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda Interspeech, Dublin, Ireland, August 2023 Paper |
|
|
A vector quantized masked autoencoder for speech emotion recognition Samir Sadok, Simon Leglaive, Renaud Séguier IEEE ICASSP 2023 Workshop on Self-Supervision in Audio, Speech and Beyond (SASB), Rhodes, Greece, June 2023 Paper | Demo | Code |
|
|
Speech modeling with a hierarchical transformer dynamical VAE Xiaoyu Lin, Xiaoyu Bie, Simon Leglaive, Laurent Girin, Xavier Alameda-Pineda IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Rhodes, Greece, June 2023 Paper |
|
| 2022 |
Expectation-maximization based defense mechanism
for distributed model predictive control Rafael Accácio Nogueira, Romain Bourdais, Simon Leglaive, Hervé Guéguen IFAC Conference on Networked Systems (NecSys22), Zürich, Switzerland, July 2022 Paper |
| 2021 |
On speech sparsity for computational efficiency and noise reduction in hearing aids Adrien Llave, Simon Leglaive Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), Tokyo, Japan, December 2021 Paper | Demo |
|
A benchmark of dynamical variational autoencoders applied to speech spectrogram modeling Xiaoyu Bie, Laurent Girin, Simon Leglaive, Thomas Hueber, Xavier Alameda-Pineda Interspeech, Brno, Czech Republic, September 2021 Paper | Code |
|
| 2020 |
Localization cues preservation in hearing aids by combining noise reduction and dynamic range compression Adrien Llave, Simon Leglaive, Renaud Séguier Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), Auckland, New Zealand, December 2020 Paper | Demo |
|
A recurrent variational autoencoder for speech enhancement Simon Leglaive, Xavier Alameda-Pineda, Laurent Girin, Radu Horaud IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Barcelona, Spain, May 2020 Paper | Demo | Code | Slides | Video |
|
| 2019 |
Notes on the use of variational autoencoders for speech and audio spectrogram modeling Laurent Girin, Thomas Hueber, Fanny Roche, Simon Leglaive International Conference on Digital Audio Effects (DAFx), Birmingham, UK, September 2019 Paper |
|
Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization Simon Leglaive, Laurent Girin, Radu Horaud IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Brighton, UK, May 2019 Paper | Demo | Code | Slides |
|
|
Speech enhancement with variational autoencoders and alpha-stable distributions Simon Leglaive, Umut Şimşekli, Antoine Liutkus, Laurent Girin, Radu Horaud IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Brighton, UK, May 2019 Paper | Demo | Code | Poster |
|
| 2018 |
A variance modeling framework based on variational autoencoders for speech enhancement Simon Leglaive, Laurent Girin, Radu Horaud IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Aalborg, Denmark, September 2018 Paper | Supp. document | Demo | Code | Slides |
|
Alpha-stable low-rank plus residual decomposition for speech enhancement Umut Şimşekli, Halil Erdoğan, Simon Leglaive, Antoine Liutkus, Roland Badeau, Gaël Richard IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Calgary, Canada, April 2018 Paper |
|
| 2017 |
Separating time-frequency sources from time-domain convolutive mixtures using non-negative matrix factorization Simon Leglaive, Roland Badeau, Gaël Richard IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA, October 2017 Paper | Supp. document | Demo | Code | Slides |
|
Semi-blind Student's t source separation for multichannel audio convolutive mixtures Simon Leglaive, Roland Badeau, Gaël Richard European Signal Processing Conference (EUSIPCO), Kos island, Greece, August 2017 Paper | Demo | Code | Slides |
|
|
Alpha-stable multichannel audio source separation Simon Leglaive, Umut Şimşekli, Antoine Liutkus, Roland Badeau, Gaël Richard IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), New-Orleans, LA, USA, March 2017 Paper | Supp. document | Poster |
|
|
Multichannel audio source separation: variational inference of time-frequency sources from time-domain observations Simon Leglaive, Roland Badeau, Gaël Richard IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), New-Orleans, LA, USA, March 2017 Paper | Demo | Code | Slides |
|
| 2016 |
Autoregressive moving average modeling of late reverberation in the frequency domain Simon Leglaive, Roland Badeau, Gaël Richard European Signal Processing Conference (EUSIPCO), Budapest, Hungary, August 2016 Paper | Poster |
| 2015 |
Multichannel audio source separation with probabilistic reverberation modeling Simon Leglaive, Roland Badeau, Gaël Richard IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA, October 2015 Paper | Slides |
|
Singing voice detection with deep recurrent neural networks Simon Leglaive, Romain Hennequin, Roland Badeau IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), Brisbane, Australia, April 2015 Paper | Slides |
National conferences
| 2023 |
Étude sur l’inversion de StyleGAN dans un contexte de détection d’hypertrucages Matthieu Delmas, Amine Kacete, Stéphane Paquelet, Simon Leglaive, Renaud Séguier XXIXe Colloque GRETSI, Grenoble, France, August-September 2023 Paper |
| 2022 |
Les auto-encodeurs variationnels dynamiques et leur application à la modélisation de spectrogrammes de parole Laurent Girin, Simon Leglaive, Xiaoyu Bie, Julien Diard, Thomas Hueber, Xavier Alameda-Pineda XXXIVe Journées d’Études sur la Parole (JEP), Île de Noirmoutier, France, June 2022 Paper |
| 2017 |
Séparation de sources audio en milieu réverbérant : Factorisation en matrices non-négatives et représentation temporelle du mélange convolutif Simon Leglaive, Roland Badeau, Gaël Richard XXVIe Colloque GRETSI, Juan-Les-Pins, France, September 2017 Paper | Demo | Code | Slides |
| 2015 |
A priori probabiliste anéchoïque pour la séparation sous-déterminée de sources sonores en milieu réverbérant Simon Leglaive, Roland Badeau, Gaël Richard XXVe Colloque GRETSI, Lyon, France, September 2015 Paper | Poster |
Theses
| 2017 |
Modèles de mélange pour la séparation multicanale de sources sonores en milieu réverbérant Ph.D. Thesis Defended on December 12, 2017 Manuscript | Slides |
| 2014 |
Work carried out at Audionamix Manuscript |