On music genre classification via compressive sampling

Bob L. Sturm

Research output: Contribution to journalConference article in JournalResearchpeer-review

7 Citations (Scopus)
667 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.
Original languageEnglish
JournalInternational Conference on Multimedia and Expo
Publication statusPublished - 2013
Event2012 IEEE Conference on Multimedia & Expo - San Jose, United States
Duration: 15 Jul 201319 Jul 2013

Conference

Conference2012 IEEE Conference on Multimedia & Expo
CountryUnited States
CitySan Jose
Period15/07/201319/07/2013

Fingerprint

Sampling
Compressed sensing
Acoustics

Cite this

@inproceedings{55d669bdb0554ea984583b92ce164675,
title = "On music genre classification via compressive sampling",
abstract = "Recent work \cite{Chang2010} combines low-level acoustic featuresand random projection (referred to as ``compressed sensing'' in \cite{Chang2010})to create a music genre classification system showingan accuracy among the highest reportedfor a benchmark dataset.This not only contradicts previous findingsthat suggest low-level features are inadequate foraddressing 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",

}

On music genre classification via compressive sampling. / Sturm, Bob L.

In: International Conference on Multimedia and Expo, 2013.

Research output: Contribution to journalConference article in JournalResearchpeer-review

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 featuresand random projection (referred to as ``compressed sensing'' in \cite{Chang2010})to create a music genre classification system showingan accuracy among the highest reportedfor a benchmark dataset.This not only contradicts previous findingsthat suggest low-level features are inadequate foraddressing 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 featuresand random projection (referred to as ``compressed sensing'' in \cite{Chang2010})to create a music genre classification system showingan accuracy among the highest reportedfor a benchmark dataset.This not only contradicts previous findingsthat suggest low-level features are inadequate foraddressing 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

ER -