2013/04/30 by Joakim Andén, Stéphane Mallat · 2 citations
Computer Science · Mathematics · #cs.IT #cs.SD #math.IT
paper · pdf · doi:10.1109/tsp.2014.2326991
arxiv created 2014/01/10 · arxiv updated 2015/06/15
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.