Audio modeling and processing

Relevant publications

Weakly supervised representation learning for audio-visual scene analysis
S. Parekh, S. Essid, A. Ozerov, N. QK Duong, P. Pérez, G. Richard
IEEE Trans. Audio, Speech and Language Processing 2020

Solving time domain audio inverse problems using nonnegative tensor factorization
C. Bilen, A. Ozerov, P. Pérez
IEEE Trans. on Signal Processing 2018

Audio style transfer
E. Grinstein, N. Duong, A. Ozerov, P. Pérez
ICASSP 2018

Motion informed audio source separation
S. Parekh, S. Essid, A. Ozerov, N. Duong, P. Pérez, G. Richard
ICASSP 2017

Informed source separation via compressive graph sampling
G. Puy, A. Ozerov, N. Duong, P. Pérez
ICASSP 2017

A comparative study of example-guided audio source separation approaches based on nonnegative matrix factorization
A. Ozerov, S. Kitic, P. Pérez
MLSP 2017

Guiding audio source separation by video object information
S. Parekh, S. Essid, A. Ozerov, N. Duong, P. Pérez, G. Richard
WASPAA 2017

Text-informed speech inpainting via voice conversion
P. Prablanc, N. Duong, A. Ozerov, P. Pérez
Eusipco 2016

Multichannel audio declipping
A. Ozerov, C. Bilen, P. Pérez
ICASSP 2016

Automatic allocation of NTF components for user-guided audio source separation
C. Bilen, A. Ozerov, P. Pérez
ICASSP 2016

Compressive sampling-based informed source separation
C. Bilen, A. Ozerov, P.Pérez
WASPAA 2015

Audio declipping via nonnegative matrix factorization
C. Bilen, A. Ozerov, P.Pérez
WASPAA 2015

Joint audio inpainting and source separation
C. Bilen, A. Ozerov, P.Pérez
LVA 2015