Two Systems for Automatic Music Genre Recognition: What Are They Really Recognizing?

Bob L. Sturm

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

23 Citationer (Scopus)
1344 Downloads (Pure)

Abstract

We re-implement and test two state-of-the-art systems
for automatic music genre classification;
but unlike past works in this area,
we look closer than ever before at their behavior.
First, we look at specific instances where
each system consistently applies the same wrong label
across multiple trials of cross-validation.
Second, we test the robustness of each system
to spectral equalization.
Finally, we test how well human subjects recognize
the genres of music excerpts composed by
each system to be highly genre representative.
Our results suggest that neither high-performing system
has a capacity to recognize music genre.
OriginalsprogEngelsk
TitelProceedings of the second international ACM workshop on Music information retrieval with user-centered and multimodal strategies
Vol/bind2012
ForlagAssociation for Computing Machinery (ACM)
Publikationsdato2012
Sider69-74
ISBN (Trykt)978-1-4503-1591-3
DOI
StatusUdgivet - 2012
BegivenhedACM Multimedia 2012: Workshop on Music Information Retrieval with User-Centered and Multimodal Strategies - Nara, Japan
Varighed: 29 okt. 20122 nov. 2012

Konference

KonferenceACM Multimedia 2012
Land/OmrådeJapan
ByNara
Periode29/10/201202/11/2012
NavnACM Multimedia

Fingeraftryk

Dyk ned i forskningsemnerne om 'Two Systems for Automatic Music Genre Recognition: What Are They Really Recognizing?'. Sammen danner de et unikt fingeraftryk.

Citationsformater