CITATION — REFERENCE ENTRY
The GTZAN dataset: Its contents, its faults, their effects on evaluation, and its future use — arXiv
- Key
- sturm2013-gtzan
- Authors
- Sturm, Bob L.
- Issued
- 2013-6-6
- Type
- article
- Container
- arXiv
Raw CSL JSON
{
"URL": "https://arxiv.org/abs/1306.1461",
"type": "article",
"title": "The GTZAN dataset: Its contents, its faults, their effects on evaluation, and its future use",
"author": [
{
"given": "Bob L.",
"family": "Sturm"
}
],
"issued": {
"date-parts": [
[
2013,
6,
6
]
]
},
"number": "1306.1461",
"container-title": "arXiv"
}
Claims
-
GTZAN is the most-used public dataset for music genre recognition evaluation, but contains repetitions, mislabelings, and distortions that affect systems differently and challenge the interpretability of results.
"The GTZAN dataset appears in at least 100 published works, and is the most-used public dataset for evaluation in machine listening research for music genre recognition (MGR). Our recent work, however, shows GTZAN has several faults (repetitions, mislabelings, and distortions), which challenge the interpretability of any result derived using it. In this article, we disprove the claims that all MGR systems are affected in the same ways by these faults"
Available in