Evaluating music emotion recognition: Lessons from music genre recognition?

Bob L. Sturm

Research output: Contribution to journalConference article in JournalResearchpeer-review

9 Citations (Scopus)
952 Downloads (Pure)

Abstract

A fundamental problem with nearly all work in music genre recognition (MGR)is that evaluation lacks validity with respect to the principal goals of MGR. This problem also occurs in the evaluation of music emotion recognition (MER). Standard approaches to evaluation, though easy to implement, do not reliably differentiate between recognizing genre or emotion from music, or by virtue of confounding factors in signals (e.g., equalization). We demonstrate such problems for evaluating an MER system, and conclude with recommendations.
Original languageEnglish
JournalInternational Conference on Multimedia and Expo
Pages (from-to)1-6
Publication statusPublished - 2013
Event2013 IEEE International Conference on Multimedia & Expo - San Jose, United States
Duration: 15 Jul 201319 Jul 2013

Conference

Conference2013 IEEE International Conference on Multimedia & Expo
CountryUnited States
CitySan Jose
Period15/07/201319/07/2013

Fingerprint

Emotion Recognition
Music
Evaluation
Fundamental
Emotion

Cite this

@inproceedings{bd617fd9b9d84a38891ab2a4e70bba10,
title = "Evaluating music emotion recognition: Lessons from music genre recognition?",
abstract = "A fundamental problem with nearly all work in music genre recognition (MGR)is that evaluation lacks validity with respect to the principal goals of MGR. This problem also occurs in the evaluation of music emotion recognition (MER). Standard approaches to evaluation, though easy to implement, do not reliably differentiate between recognizing genre or emotion from music, or by virtue of confounding factors in signals (e.g., equalization). We demonstrate such problems for evaluating an MER system, and conclude with recommendations.",
author = "Sturm, {Bob L.}",
year = "2013",
language = "English",
pages = "1--6",
journal = "International Conference on Multimedia and Expo",
publisher = "IEEE",

}

Evaluating music emotion recognition : Lessons from music genre recognition? . / Sturm, Bob L.

In: International Conference on Multimedia and Expo, 2013, p. 1-6.

Research output: Contribution to journalConference article in JournalResearchpeer-review

TY - GEN

T1 - Evaluating music emotion recognition

T2 - Lessons from music genre recognition?

AU - Sturm, Bob L.

PY - 2013

Y1 - 2013

N2 - A fundamental problem with nearly all work in music genre recognition (MGR)is that evaluation lacks validity with respect to the principal goals of MGR. This problem also occurs in the evaluation of music emotion recognition (MER). Standard approaches to evaluation, though easy to implement, do not reliably differentiate between recognizing genre or emotion from music, or by virtue of confounding factors in signals (e.g., equalization). We demonstrate such problems for evaluating an MER system, and conclude with recommendations.

AB - A fundamental problem with nearly all work in music genre recognition (MGR)is that evaluation lacks validity with respect to the principal goals of MGR. This problem also occurs in the evaluation of music emotion recognition (MER). Standard approaches to evaluation, though easy to implement, do not reliably differentiate between recognizing genre or emotion from music, or by virtue of confounding factors in signals (e.g., equalization). We demonstrate such problems for evaluating an MER system, and conclude with recommendations.

M3 - Conference article in Journal

SP - 1

EP - 6

JO - International Conference on Multimedia and Expo

JF - International Conference on Multimedia and Expo

ER -