A comparison of audio signal preprocessing methods for deep neural networks on music tagging

Keunwoo Choi, György Fazekas, Mark Sandler, Kyunghyun Cho

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting, and scaling. We show that many commonly used input preprocessing techniques are redundant except magnitude compression.

Original languageEnglish (US)
Title of host publication2018 26th European Signal Processing Conference, EUSIPCO 2018
PublisherEuropean Signal Processing Conference, EUSIPCO
Pages1870-1874
Number of pages5
Volume2018-September
ISBN (Electronic)9789082797015
DOIs
StatePublished - Nov 29 2018
Event26th European Signal Processing Conference, EUSIPCO 2018 - Rome, Italy
Duration: Sep 3 2018Sep 7 2018

Other

Other26th European Signal Processing Conference, EUSIPCO 2018
CountryItaly
CityRome
Period9/3/189/7/18

Fingerprint

Experiments
Deep neural networks

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Choi, K., Fazekas, G., Sandler, M., & Cho, K. (2018). A comparison of audio signal preprocessing methods for deep neural networks on music tagging. In 2018 26th European Signal Processing Conference, EUSIPCO 2018 (Vol. 2018-September, pp. 1870-1874). [8553106] European Signal Processing Conference, EUSIPCO. https://doi.org/10.23919/EUSIPCO.2018.8553106

A comparison of audio signal preprocessing methods for deep neural networks on music tagging. / Choi, Keunwoo; Fazekas, György; Sandler, Mark; Cho, Kyunghyun.

2018 26th European Signal Processing Conference, EUSIPCO 2018. Vol. 2018-September European Signal Processing Conference, EUSIPCO, 2018. p. 1870-1874 8553106.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Choi, K, Fazekas, G, Sandler, M & Cho, K 2018, A comparison of audio signal preprocessing methods for deep neural networks on music tagging. in 2018 26th European Signal Processing Conference, EUSIPCO 2018. vol. 2018-September, 8553106, European Signal Processing Conference, EUSIPCO, pp. 1870-1874, 26th European Signal Processing Conference, EUSIPCO 2018, Rome, Italy, 9/3/18. https://doi.org/10.23919/EUSIPCO.2018.8553106
Choi K, Fazekas G, Sandler M, Cho K. A comparison of audio signal preprocessing methods for deep neural networks on music tagging. In 2018 26th European Signal Processing Conference, EUSIPCO 2018. Vol. 2018-September. European Signal Processing Conference, EUSIPCO. 2018. p. 1870-1874. 8553106 https://doi.org/10.23919/EUSIPCO.2018.8553106
Choi, Keunwoo ; Fazekas, György ; Sandler, Mark ; Cho, Kyunghyun. / A comparison of audio signal preprocessing methods for deep neural networks on music tagging. 2018 26th European Signal Processing Conference, EUSIPCO 2018. Vol. 2018-September European Signal Processing Conference, EUSIPCO, 2018. pp. 1870-1874
@inproceedings{aec1fe0088b44ccd990425982d23f61e,
title = "A comparison of audio signal preprocessing methods for deep neural networks on music tagging",
abstract = "In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting, and scaling. We show that many commonly used input preprocessing techniques are redundant except magnitude compression.",
author = "Keunwoo Choi and Gy{\"o}rgy Fazekas and Mark Sandler and Kyunghyun Cho",
year = "2018",
month = "11",
day = "29",
doi = "10.23919/EUSIPCO.2018.8553106",
language = "English (US)",
volume = "2018-September",
pages = "1870--1874",
booktitle = "2018 26th European Signal Processing Conference, EUSIPCO 2018",
publisher = "European Signal Processing Conference, EUSIPCO",

}

TY - GEN

T1 - A comparison of audio signal preprocessing methods for deep neural networks on music tagging

AU - Choi, Keunwoo

AU - Fazekas, György

AU - Sandler, Mark

AU - Cho, Kyunghyun

PY - 2018/11/29

Y1 - 2018/11/29

N2 - In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting, and scaling. We show that many commonly used input preprocessing techniques are redundant except magnitude compression.

AB - In this paper, we empirically investigate the effect of audio preprocessing on music tagging with deep neural networks. We perform comprehensive experiments involving audio preprocessing using different time-frequency representations, logarithmic magnitude compression, frequency weighting, and scaling. We show that many commonly used input preprocessing techniques are redundant except magnitude compression.

UR - http://www.scopus.com/inward/record.url?scp=85059824782&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059824782&partnerID=8YFLogxK

U2 - 10.23919/EUSIPCO.2018.8553106

DO - 10.23919/EUSIPCO.2018.8553106

M3 - Conference contribution

AN - SCOPUS:85059824782

VL - 2018-September

SP - 1870

EP - 1874

BT - 2018 26th European Signal Processing Conference, EUSIPCO 2018

PB - European Signal Processing Conference, EUSIPCO

ER -