English

Transform\'ee en scattering sur la spirale temps-chroma-octave

Sound 2015-09-02 v1

Abstract

We introduce a scattering representation for the analysis and classification of sounds. It is locally translation-invariant, stable to deformations in time and frequency, and has the ability to capture harmonic structures. The scattering representation can be interpreted as a convolutional neural network which cascades a wavelet transform in time and along a harmonic spiral. We study its application for the analysis of the deformations of the source-filter model.

Keywords

Cite

@article{arxiv.1509.00334,
  title  = {Transform\'ee en scattering sur la spirale temps-chroma-octave},
  author = {Vincent Lostanlen and Stéphane Mallat},
  journal= {arXiv preprint arXiv:1509.00334},
  year   = {2015}
}

Comments

in French, 4 pages, 3 figures, presented at GRETSI 2015 in Lyon, France

R2 v1 2026-06-22T10:46:32.084Z