A Closer Look at Deep Learning Neural Networks with Low-level Spectral Periodicity Features

Bob L. Sturm; Corey Kereliuk; Aggelos Pikrakis

doi:10.1109/CIP.2014.6844511

A Closer Look at Deep Learning Neural Networks with Low-level Spectral Periodicity Features

Bob L. Sturm, Corey Kereliuk, Aggelos Pikrakis

Department of Architecture, Design and Media Technology

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

8 Citations (Scopus)

Abstract

Systems built using deep learning neural networks trained on low-level spectral periodicity features (DeSPerF) reproduced the most “ground truth” of the systems submitted to the MIREX 2013 task, “Audio Latin Genre Classification.” To answer why this was the case, we take a closer look at the behavior of a DeSPerF system we create and evaluate using the benchmark dataset BALLROOM. We find through time stretching that this DeSPerF system appears to obtain a high figure of merit on the task of music genre recognition because of a confounding of tempo with “ground truth” in BALLROOM. This observation motivates several predictions.

Original language	English
Title of host publication	Proceedings of 4th International Workshop on Cognitive Information Processing (CIP 2014)
Editors	Lars Kai Hansen, Søren Holdt Jensen, Jan Larsen
Number of pages	6
Volume	1
Publisher	IEEE
Publication date	2014
Pages	1-6
ISBN (Print)	978-1-4799-3696-0
DOIs	https://doi.org/10.1109/CIP.2014.6844511
Publication status	Published - 2014
Event	International Workshop on Cognitive Information Processing - Bella Sky Hotel, Copenhagen, Denmark Duration: 26 May 2014 → 28 May 2014

Conference

Conference	International Workshop on Cognitive Information Processing
Location	Bella Sky Hotel
Country/Territory	Denmark
City	Copenhagen
Period	26/05/2014 → 28/05/2014

Access to Document

10.1109/CIP.2014.6844511

AUB Link

Search for the material in Aalborg University Library's search engine

CoSound
Christensen, M. G., Tan, Z., Jensen, S. H. & Sturm, B. L.
01/01/2012 → 31/12/2015
Project: Research

Cite this

@inproceedings{f093c813f3c64c4fb9a4515ab720ff45,

title = "A Closer Look at Deep Learning Neural Networks with Low-level Spectral Periodicity Features",

abstract = "Systems built using deep learning neural networks trained on low-level spectral periodicity features (DeSPerF) reproduced the most “ground truth” of the systems submitted to the MIREX 2013 task, “Audio Latin Genre Classification.” To answer why this was the case, we take a closer look at the behavior of a DeSPerF system we create and evaluate using the benchmark dataset BALLROOM. We find through time stretching that this DeSPerF system appears to obtain a high figure of merit on the task of music genre recognition because of a confounding of tempo with “ground truth” in BALLROOM. This observation motivates several predictions.",

author = "Sturm, {Bob L.} and Corey Kereliuk and Aggelos Pikrakis",

year = "2014",

doi = "10.1109/CIP.2014.6844511",

language = "English",

isbn = "978-1-4799-3696-0",

volume = "1",

pages = "1--6",

editor = "Hansen, {Lars Kai} and {Holdt Jensen}, {S{\o}ren } and Jan Larsen",

booktitle = "Proceedings of 4th International Workshop on Cognitive Information Processing (CIP 2014)",

publisher = "IEEE",

address = "United States",

note = "International Workshop on Cognitive Information Processing ; Conference date: 26-05-2014 Through 28-05-2014",

}

Sturm, BL, Kereliuk, C & Pikrakis, A 2014, A Closer Look at Deep Learning Neural Networks with Low-level Spectral Periodicity Features. in LK Hansen, S Holdt Jensen & J Larsen (eds), Proceedings of 4th International Workshop on Cognitive Information Processing (CIP 2014). vol. 1, IEEE, pp. 1-6, International Workshop on Cognitive Information Processing, Copenhagen, Denmark, 26/05/2014. https://doi.org/10.1109/CIP.2014.6844511

A Closer Look at Deep Learning Neural Networks with Low-level Spectral Periodicity Features. / Sturm, Bob L.; Kereliuk, Corey; Pikrakis, Aggelos.
Proceedings of 4th International Workshop on Cognitive Information Processing (CIP 2014). ed. / Lars Kai Hansen; Søren Holdt Jensen; Jan Larsen. Vol. 1 IEEE, 2014. p. 1-6.

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - A Closer Look at Deep Learning Neural Networks with Low-level Spectral Periodicity Features

AU - Sturm, Bob L.

AU - Kereliuk, Corey

AU - Pikrakis, Aggelos

PY - 2014

Y1 - 2014

N2 - Systems built using deep learning neural networks trained on low-level spectral periodicity features (DeSPerF) reproduced the most “ground truth” of the systems submitted to the MIREX 2013 task, “Audio Latin Genre Classification.” To answer why this was the case, we take a closer look at the behavior of a DeSPerF system we create and evaluate using the benchmark dataset BALLROOM. We find through time stretching that this DeSPerF system appears to obtain a high figure of merit on the task of music genre recognition because of a confounding of tempo with “ground truth” in BALLROOM. This observation motivates several predictions.

AB - Systems built using deep learning neural networks trained on low-level spectral periodicity features (DeSPerF) reproduced the most “ground truth” of the systems submitted to the MIREX 2013 task, “Audio Latin Genre Classification.” To answer why this was the case, we take a closer look at the behavior of a DeSPerF system we create and evaluate using the benchmark dataset BALLROOM. We find through time stretching that this DeSPerF system appears to obtain a high figure of merit on the task of music genre recognition because of a confounding of tempo with “ground truth” in BALLROOM. This observation motivates several predictions.

U2 - 10.1109/CIP.2014.6844511

DO - 10.1109/CIP.2014.6844511

M3 - Article in proceeding

SN - 978-1-4799-3696-0

VL - 1

SP - 1

EP - 6

BT - Proceedings of 4th International Workshop on Cognitive Information Processing (CIP 2014)

A2 - Hansen, Lars Kai

A2 - Holdt Jensen, Søren

A2 - Larsen, Jan

PB - IEEE

T2 - International Workshop on Cognitive Information Processing

Y2 - 26 May 2014 through 28 May 2014

ER -

A Closer Look at Deep Learning Neural Networks with Low-level Spectral Periodicity Features

Abstract

Conference

Access to Document

AUB Link

Fingerprint

Projects

CoSound

Cite this