CITATION — REFERENCE ENTRY
The State of the Art Ten Years After a State of the Art: Future Research in Music Information Retrieval — Journal of New Music Research
- Key
- sturm2014-mgr-ten-years
- Authors
- Sturm, Bob L.
- Issued
- 2014
- Type
- article-journal
- Container
- Journal of New Music Research
- Volume
- 43
- Issue
- 2
- Pages
- 147-172
Raw CSL JSON
{
"DOI": "10.1080/09298215.2014.894533",
"page": "147-172",
"type": "article-journal",
"issue": "2",
"title": "The State of the Art Ten Years After a State of the Art: Future Research in Music Information Retrieval",
"author": [
{
"given": "Bob L.",
"family": "Sturm"
}
],
"issued": {
"date-parts": [
[
2014
]
]
},
"volume": "43",
"container-title": "Journal of New Music Research"
}
Claims
-
Despite about 500 published works, music genre recognition has not progressed far, chiefly because most evaluation lacks validity; similar validity problems affect music emotion recognition and autotagging.
"During this time, about 500 works addressing MGR have been published [...] We show that in spite of this massive amount of work, MGR does not lie far from where it began, and the paramount reason for this is that most evaluation in MGR lacks validity. [...] In fact, the problems of validity in evaluation also affect research in music emotion recognition and autotagging."
Available in