On music genre classification via compressive sampling

Bob L. Sturm

On music genre classification via compressive sampling

Bob L. Sturm

Institut for Arkitektur, Design og Medieteknologi

Publikation: Bidrag til tidsskrift › Konferenceartikel i tidsskrift › Forskning › peer review

17 Citationer (Scopus)

1196 Downloads (Pure)

Abstract

Recent work \cite{Chang2010} combines low-level acoustic features
and random projection (referred to as ``compressed sensing'' in \cite{Chang2010})
to create a music genre classification system showing
an accuracy among the highest reported
for a benchmark dataset.
This not only contradicts previous findings
that suggest low-level features are inadequate for
addressing high-level musical problems,
but also that a random projection of features
can improve classification.
We reproduce this work and resolve these contradictions.

Originalsprog	Engelsk
Tidsskrift	International Conference on Multimedia and Expo
Status	Udgivet - 2013
Begivenhed	2012 IEEE Conference on Multimedia & Expo - San Jose, USA Varighed: 15 jul. 2013 → 19 jul. 2013

Konference

Konference	2012 IEEE Conference on Multimedia & Expo
Land/Område	USA
By	San Jose
Periode	15/07/2013 → 19/07/2013

Adgang til dokumentet

CSgenre20130312Indsendt manuskript, 324 KB

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

CoSound
Christensen, M. G. (Projektdeltager), Tan, Z.-H. (Projektdeltager), Jensen, S. H. (Projektdeltager) & Sturm, B. L. (Projektdeltager)
01/01/2012 → 31/12/2015
Projekter: Projekt › Forskning
Greedy Sparse Approximation and the Automatic Description of Audio and Music Data
Sturm, B. L. (Projektdeltager)
Technology and Production Independent Postdoc Center for Independent Research
01/01/2012 → 01/01/2015
Projekter: Projekt › Forskning

Citationsformater

@inproceedings{55d669bdb0554ea984583b92ce164675,

title = "On music genre classification via compressive sampling",

abstract = "Recent work \textbackslash{}cite\{Chang2010\} combines low-level acoustic features and random projection (referred to as ``compressed sensing'' in \textbackslash{}cite\{Chang2010\}) to create a music genre classification system showing an accuracy among the highest reported for a benchmark dataset. This not only contradicts previous findings that suggest low-level features are inadequate for addressing high-level musical problems, but also that a random projection of features can improve classification. We reproduce this work and resolve these contradictions.",

author = "Sturm, \{Bob L.\}",

year = "2013",

language = "English",

journal = "International Conference on Multimedia and Expo",

publisher = "IEEE (Institute of Electrical and Electronics Engineers)",

note = "2012 IEEE Conference on Multimedia \& Expo ; Conference date: 15-07-2013 Through 19-07-2013",

}

TY - GEN

T1 - On music genre classification via compressive sampling

AU - Sturm, Bob L.

PY - 2013

Y1 - 2013

N2 - Recent work \cite{Chang2010} combines low-level acoustic features and random projection (referred to as ``compressed sensing'' in \cite{Chang2010}) to create a music genre classification system showing an accuracy among the highest reported for a benchmark dataset. This not only contradicts previous findings that suggest low-level features are inadequate for addressing high-level musical problems, but also that a random projection of features can improve classification. We reproduce this work and resolve these contradictions.

AB - Recent work \cite{Chang2010} combines low-level acoustic features and random projection (referred to as ``compressed sensing'' in \cite{Chang2010}) to create a music genre classification system showing an accuracy among the highest reported for a benchmark dataset. This not only contradicts previous findings that suggest low-level features are inadequate for addressing high-level musical problems, but also that a random projection of features can improve classification. We reproduce this work and resolve these contradictions.

M3 - Conference article in Journal

JO - International Conference on Multimedia and Expo

JF - International Conference on Multimedia and Expo

T2 - 2012 IEEE Conference on Multimedia & Expo

Y2 - 15 July 2013 through 19 July 2013

ER -

On music genre classification via compressive sampling

Abstract

Konference

Adgang til dokumentet

AUB Link

Fingeraftryk

Projekter

CoSound

Greedy Sparse Approximation and the Automatic Description of Audio and Music Data

Citationsformater