Deep Scattering Spectrum

DOI10.1109/TSP.2014.2326991zbMATH Open1394.94040arXiv1304.6763MaRDI QIDQ4579374FDOQ4579374

Authors: Joakim Andén, Stéphane Mallat 

Publication date: 22 August 2018

Published in: IEEE Transactions on Signal Processing (Search for Journal in Brave)

Abstract: A scattering transform defines a locally translation invariant representation which is stable to time-warping deformations. It extends MFCC representations by computing modulation spectrum coefficients of multiple orders, through cascades of wavelet convolutions and modulus operators. Second-order scattering coefficients characterize transient phenomena such as attacks and amplitude modulation. A frequency transposition invariant representation is obtained by applying a scattering transform along log-frequency. State-the-of-art classification results are obtained for musical genre and phone classification on GTZAN and TIMIT databases, respectively.

Full work available at URL: https://arxiv.org/abs/1304.6763

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Cited In (19)

• Multiscale sparse microcanonical models
• Wavelet scattering transform and ensemble methods for side-channel analysis
• Phase retrieval for the Cauchy wavelet transform
• When scattering transform meets non-Gaussian random processes, a double scaling limit result
• Asymptotic analysis of higher-order scattering transform of Gaussian processes
• Asymptotic Links between Signal Processing, Acoustic Metamaterials, and Biology
• Intermittent process analysis with scattering moments
• Can generalised divergences help for invariant neural networks?
• Spectrum bottom and largest vacuity
• Constant rank factorisations of smooth maps, with applications to sonar
• ScatNet
• Bernhard Riemann, the ear, and an atom of consciousness
• Wavelet Scattering Regression of Quantum Chemical Energies
• Rotationally invariant time-frequency scattering transforms
• Approximation by group invariant subspaces
• Gaussian approximation for the moving averaged modulus wavelet transform and its variants
• Continuous Generative Neural Networks: A Wavelet-Based Architecture in Function Spaces
• Bioinspired Random Projections for Robust, Sparse Classification
• Central and Noncentral Limit Theorems Arising from the Scattering Transform and Its Neural Activation Generalization

This page was built for publication: Deep Scattering Spectrum

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4579374)