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

Bob L. Sturm, Corey Kereliuk, Aggelos Pikrakis

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

8 Citationer (Scopus)

Abstrakt

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.
OriginalsprogEngelsk
TitelProceedings of 4th International Workshop on Cognitive Information Processing (CIP 2014)
RedaktørerLars Kai Hansen, Søren Holdt Jensen, Jan Larsen
Antal sider6
Vol/bind1
ForlagIEEE
Publikationsdato2014
Sider1-6
ISBN (Trykt)978-1-4799-3696-0
DOI
StatusUdgivet - 2014
BegivenhedInternational Workshop on Cognitive Information Processing - Bella Sky Hotel, Copenhagen, Danmark
Varighed: 26 maj 201428 maj 2014

Konference

KonferenceInternational Workshop on Cognitive Information Processing
LokationBella Sky Hotel
LandDanmark
ByCopenhagen
Periode26/05/201428/05/2014

Fingeraftryk

Dyk ned i forskningsemnerne om 'A Closer Look at Deep Learning Neural Networks with Low-level Spectral Periodicity Features'. Sammen danner de et unikt fingeraftryk.
  • CoSound

    Christensen, M. G., Tan, Z., Jensen, S. H. & Sturm, B. L.

    01/01/201231/12/2015

    Projekter: ProjektForskning

Citationsformater