Evaluating music emotion recognition: Lessons from music genre recognition?

Research output: Contribution to journalConference article in Journal

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.
Close

Details

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
StatePublished - 2013
Publication categoryResearch
Peer-reviewedYes
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

Activities

Projects

Download statistics

No data available
ID: 75592185