Gabor frames and deep scattering networks in audio processing

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F19%3APU133538" target="_blank" >RIV/00216305:26220/19:PU133538 - isvavai.cz</a>

Result on the web

<a href="https://www.mdpi.com/2075-1680/8/4/106" target="_blank" >https://www.mdpi.com/2075-1680/8/4/106</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3390/axioms8040106" target="_blank" >10.3390/axioms8040106</a>

Result language

angličtina

Original language name

Gabor frames and deep scattering networks in audio processing

Original language description

This paper introduces Gabor scattering, a feature extractor based on Gabor frames and Mallat's scattering transform. By using a simple signal model for audio signals specific properties of Gabor scattering are studied. It is shown that for each layer, specific invariances to certain signal characteristics occur. Furthermore, deformation stability of the coefficient vector generated by the feature extractor is derived by using a decoupling technique which exploits the contractivity of general scattering networks. Deformations are introduced as changes in spectral shape and frequency modulation. The theoretical results are illustrated by numerical examples and experiments. Numerical evidence is given by evaluation on a synthetic and a "real" data set, that the invariances encoded by the Gabor scattering transform lead to higher performance in comparison with just using Gabor transform, especially when few training samples are available.

Czech name

—

Czech description

—

Type

J_ost - Miscellaneous article in a specialist periodical

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/LO1401" target="_blank" >LO1401: Interdisciplinary Research of Wireless Technologies</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year

2019

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

Axioms

ISSN

2075-1680

e-ISSN

—

Volume of the periodical

8(4)

Issue of the periodical within the volume

106

Country of publishing house

CH - SWITZERLAND

Number of pages

25

Pages from-to

1-25

UT code for WoS article

—

EID of the result in the Scopus database

—