Deep Scattering Spectrum
Deep Scattering Spectrum
复制标题
DOI：
10.1109/tsp.2014.2326991
复制
发表时间：
2014-08-15
影响因子：
5.4
通讯作者：
Mallat, Stephane
中科院分区：
文献类型：
--
作者：
Anden, Joakim;Mallat, Stephane
散射变换定义了一个局部平移不变的表示，这是稳定的时间扭曲变形。它扩展了MFCC表示计算调制谱系数的多个订单，通过级联的小波卷积和模运算。二阶散射系数表征瞬态现象，如攻击和幅度调制。通过沿对数频率沿着进行散射变换，得到频率转置不变表示。国家的最先进的分类结果，获得音乐流派和电话分类GTZAN和TIMIT数据库，分别。
A scattering transform defines a locally translation invariant representation which is stable to time-warping deformation. 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.