Follow
Alexandre Défossez
Alexandre Défossez
Meta
Verified email at fb.com - Homepage
Title
Cited by
Cited by
Year
Music Source Separation in the Waveform Domain
A Défossez, N Usunier, L Bottou, F Bach
arXiv preprint arXiv:1911.13254, 2019
1302019
Real time speech enhancement in the waveform domain
A Défossez, G Synnaeve, Y Adi
arXiv preprint arXiv:2006.12847, 2020
1172020
Averaged least-mean-squares: Bias-variance trade-offs and optimal sampling distributions
A Défossez, F Bach
Artificial Intelligence and Statistics, 205-213, 2015
642015
A Simple Convergence Proof of Adam and Adagrad
A Défossez, L Bottou, F Bach, N Usunier
arXiv preprint arXiv:2003.02395, 2020
63*2020
SING: Symbol-to-Instrument Neural Generator
A Défossez, N Zeghidour, N Usunier, L Bottou, F Bach
Advances in Neural Information Processing Systems, 9055-9065, 2018
452018
Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed
A Défossez, N Usunier, L Bottou, F Bach
arXiv preprint arXiv:1909.01174, 2019
392019
Regression versus classification for neural network based audio source localization
L Perotin, A Défossez, E Vincent, R Serizel, A Guérin
2019 IEEE Workshop on Applications of Signal Processing to Audio and …, 2019
212019
AdaBatch: Efficient Gradient Aggregation Rules for Sequential and Parallel Stochastic Gradient Methods
A Défossez, F Bach
arXiv preprint arXiv:1711.01761, 2017
132017
Hybrid Spectrogram and Waveform Source Separation
A Défossez
arXiv preprint arXiv:2111.03600, 2021
112021
Constant step size least-mean-square: Bias-variance trade-offs and optimal sampling distributions
A Défossez, F Bach
arXiv preprint arXiv:1412.0156, 2014
102014
Differentiable Model Compression via Pseudo Quantization Noise
A Défossez, Y Adi, G Synnaeve
arXiv preprint arXiv:2104.09987, 2021
92021
Music demixing challenge 2021
Y Mitsufuji, G Fabbro, S Uhlich, FR Stöter, A Défossez, M Kim, W Choi, ...
Frontiers in Signal Processing, 18, 2022
82022
Selection and modification of features used by one or more machine learned models used by an online system
H Mehanna, SM Bowers, A Defossez, P Oberoi, O Jin
US Patent 10,002,329, 2018
22018
Deep Recurrent Encoder: A scalable end-to-end network to model brain signals
O Chehab, A Defossez, JC Loiseau, A Gramfort, JR King
arXiv preprint arXiv:2103.02339, 2021
12021
Implicit Neural Spatial Filtering for Multichannel Source Separation in the Waveform Domain
D Markovic, A Defossez, A Richard
arXiv preprint arXiv:2206.15423, 2022
2022
Optimization of Fast Deep Learning Models for Audio Analysis and Synthesis
A Défossez
Ecole Normale Supérieure, 2020
2020
The system can't perform the operation now. Try again later.
Articles 1–16