2015/09/01 by Vincent Lostanlen, Lostanlen, Vincent, Stéphane Mallat +1
Computer Science · Engineering · #Advanced Optical Imaging Technologies #Advanced Vision and Imaging #FOS: Computer and information sciences #Optical measurement and interference techniques #Sound (cs.SD)
paper · pdf · doi:10.48550/arxiv.1509.00334
openalex publication_date 2015/09/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.