Joakim Andén

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.

TL;DR: An application to genre classification shows that second-order cooccurrence coefficients improve results obtained by MFCC and Delta-MFCC descriptors.

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.

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.

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.