J
Joakim Andén
Researcher at Royal Institute of Technology
Publications - 45
Citations - 1353
Joakim Andén is an academic researcher from Royal Institute of Technology. The author has contributed to research in topics: Wavelet & Multitaper. The author has an hindex of 14, co-authored 42 publications receiving 969 citations. Previous affiliations of Joakim Andén include Princeton University & École Normale Supérieure.
Papers
More filters
Journal ArticleDOI
Deep Scattering Spectrum
Joakim Andén,Stéphane Mallat +1 more
TL;DR: A scattering transform defines a locally translation invariant representation which is stable to time-warping deformation and extends MFCC representations by computing modulation spectrum coefficients of multiple orders, through cascades of wavelet convolutions and modulus operators.
Proceedings Article
Multiscale Scattering for Audio Classification.
Joakim Andén,Stéphane Mallat +1 more
TL;DR: An application to genre classification shows that second-order cooccurrence coefficients improve results obtained by MFCC and Delta-MFCC descriptors.
Journal ArticleDOI
Scattering Transform for Intrapartum Fetal Heart Rate Variability Fractal Analysis: A Case-Control Study
TL;DR: Applied to an FHR signal database constructed in a French academic hospital, the scattering transform is shown to permit to efficiently measure scaling exponents characterizing the fractal properties of intrapartum FHR temporal dynamics, that relate not only to the sole covariance but also to the full dependence structure of data.
Journal Article
Kymatio: Scattering Transforms in Python
Mathieu Andreux,Tomás Angles,Georgios Exarchakis,Roberto Leonarduzzi,Gaspar Rochette,Louis Thiry,John Zarka,Stéphane Mallat,Stéphane Mallat,Joakim Andén,Eugene Belilovsky,Joan Bruna,Vincent Lostanlen,Muawiz Sajjad Chaudhary,Matthew J. Hirn,Edouard Oyallon,Sixin Zhang,Carmine-Emanuele Cella,Michael Eickenberg +18 more
TL;DR: Kymatio as mentioned in this paper is an easy-to-use, high-performance Python implementation of the wavelet scattering transform in 1D, 2D, and 3D that is compatible with modern deep learning frameworks.
Posted Content
Kymatio: Scattering Transforms in Python
Mathieu Andreux,Tomás Angles,Georgios Exarchakis,Roberto Leonarduzzi,Gaspar Rochette,Louis Thiry,John Zarka,Stéphane Mallat,Joakim Andén,Eugene Belilovsky,Joan Bruna,Vincent Lostanlen,Matthew J. Hirn,Edouard Oyallon,Sixhin Zhang,Carmine Cella,Michael Eickenberg +16 more
TL;DR: The Kymatio software package is presented, an easy-to-use, high-performance Python implementation of the scattering transform in 1D, 2D, and 3D that is compatible with modern deep learning frameworks.