Suivre
Simon Leglaive
Simon Leglaive
CentraleSupélec - IETR (UMR CNRS 6164)
Adresse e-mail validée de centralesupelec.fr - Page d'accueil
Titre
Citée par
Citée par
Année
Dynamical variational autoencoders: A comprehensive review
L Girin, S Leglaive, X Bie, J Diard, T Hueber, X Alameda-Pineda
Foundations and Trends in Machine Learning 15 (1-2), 1-175, 2021
1972021
Singing voice detection with deep recurrent neural networks
S Leglaive, R Hennequin, R Badeau
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
1192015
A variance modeling framework based on variational autoencoders for speech enhancement
S Leglaive, L Girin, R Horaud
2018 IEEE 28th International Workshop on Machine Learning for Signal …, 2018
962018
A recurrent variational autoencoder for speech enhancement
S Leglaive, X Alameda-Pineda, L Girin, R Horaud
2020 IEEE International Conference on Acoustics, Speech and Signal …, 2020
872020
Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization
S Leglaive, L Girin, R Horaud
2019 IEEE International Conference on Acoustics, Speech and Signal …, 2019
832019
Audio-visual speech enhancement using conditional variational auto-encoders
M Sadeghi, S Leglaive, X Alameda-Pineda, L Girin, R Horaud
IEEE/ACM Transactions on Audio, Speech and Language Processing, 2020
722020
Speech enhancement with variational autoencoders and alpha-stable distributions
S Leglaive, U Simsekli, A Liutkus, L Girin, R Horaud
2019 IEEE International Conference on Acoustics, Speech and Signal …, 2019
442019
Unsupervised speech enhancement using dynamical variational autoencoders
X Bie, S Leglaive, X Alameda-Pineda, L Girin
IEEE/ACM Transactions on Audio, Speech and Language Processing, 2022
392022
Alpha-stable multichannel audio source separation
S Leglaive, U Şimşekli, A Liutkus, R Badeau, G Richard
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
332017
Notes on the use of variational autoencoders for speech and audio spectrogram modeling
L Girin, T Hueber, F Roche, S Leglaive
International Conference on Digital Audio Effects (DAFx), 2019
272019
Multichannel audio source separation with probabilistic reverberation priors
S Leglaive, R Badeau, G Richard
IEEE/ACM Transactions on Audio, Speech, and Language Processing 24 (12 …, 2016
272016
HiT-DVAE: Human Motion Generation via Hierarchical Transformer Dynamical VAE
X Bie, W Guo, S Leglaive, L Girin, F Moreno-Noguer, X Alameda-Pineda
arXiv preprint arXiv:2204.01565, 2022
152022
Multichannel audio source separation with probabilistic reverberation modeling
S Leglaive, R Badeau, G Richard
2015 IEEE Workshop on Applications of Signal Processing to Audio and …, 2015
152015
A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modeling
X Bie, L Girin, S Leglaive, T Hueber, X Alameda-Pineda
Interspeech, 2021
142021
Student's t Source and Mixing Models for Multichannel Audio Source Separation
S Leglaive, R Badeau, G Richard
IEEE/ACM Transactions on Audio, Speech and Language Processing 26 (5), 1-15, 2018
142018
Separating time-frequency sources from time-domain convolutive mixtures using non-negative matrix factorization
S Leglaive, R Badeau, G Richard
2017 IEEE Workshop on Applications of Signal Processing to Audio and …, 2017
132017
Audio-noise Power Spectral Density Estimation Using Long Short-term Memory
X Li, S Leglaive, L Girin, R Horaud
IEEE Signal Processing Letters 26 (6), 918-922, 2019
112019
Multichannel audio source separation: variational inference of time-frequency sources from time-domain observations
S Leglaive, R Badeau, G Richard
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
112017
Learning and controlling the source-filter representation of speech with a variational autoencoder
S Sadok, S Leglaive, L Girin, X Alameda-Pineda, R Séguier
Speech Communication 148, 2023
92023
A vector quantized masked autoencoder for speech emotion recognition
S Sadok, S Leglaive, R Séguier
IEEE ICASSP 2023 Workshop on Self-Supervision in Audio, Speech and Beyond (SASB), 2023
82023
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20