Detail publikačního výsledku

Gabor frames and deep scattering networks in audio processing

BAMMER, R.; DÖRFLER, M.; HARÁR, P.

Originální název

Gabor frames and deep scattering networks in audio processing

Anglický název

Gabor frames and deep scattering networks in audio processing

Druh

Článek WoS

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

machine learning; scattering transform; Gabor transform; deep learning; time-frequency analysis; CNN;

Klíčová slova v angličtině

machine learning; scattering transform; Gabor transform; deep learning; time-frequency analysis; CNN;

Autoři

BAMMER, R.; DÖRFLER, M.; HARÁR, P.

Rok RIV

2020

Vydáno

26.09.2019

Nakladatel

MDPI

Místo

Switzerland

ISSN

2075-1680

Periodikum

Axioms

Svazek

8

Číslo

4

Stát

Švýcarská konfederace

Strany od

1

Strany do

25

Strany počet

25

URL

https://www.mdpi.com/2075-1680/8/4/106

Plný text v Digitální knihovně

http://hdl.handle.net/11012/194791

BibTex

@article{BUT159057,
  author="Roswitha {Bammer} and Monika {Dörfler} and Pavol {Harár}",
  title="Gabor frames and deep scattering networks in audio processing",
  journal="Axioms",
  year="2019",
  volume="8",
  number="4",
  pages="1--25",
  doi="10.3390/axioms8040106",
  url="https://www.mdpi.com/2075-1680/8/4/106"
}

Dokumenty

axioms-08-00106-v2