CITATION — REFERENCE ENTRY
Sound Event Detection: A tutorial — IEEE Signal Processing Magazine
- Key
- mesaros2021-sed
- Authors
- Mesaros, Annamaria; Heittola, Toni; Virtanen, Tuomas; Plumbley, Mark D.
- Issued
- 2021-9
- Type
- article-journal
- Container
- IEEE Signal Processing Magazine
- Volume
- 38
- Issue
- 5
- Pages
- 67-83
Raw CSL JSON
{
"DOI": "10.1109/MSP.2021.3090678",
"URL": "https://arxiv.org/abs/2107.05463",
"note": "Claims verified from arXiv 2107.05463 v1; page locators refer to that version.",
"page": "67-83",
"type": "article-journal",
"issue": "5",
"title": "Sound Event Detection: A tutorial",
"author": [
{
"given": "Annamaria",
"family": "Mesaros"
},
{
"given": "Toni",
"family": "Heittola"
},
{
"given": "Tuomas",
"family": "Virtanen"
},
{
"given": "Mark D.",
"family": "Plumbley"
}
],
"issued": {
"date-parts": [
[
2021,
9
]
]
},
"volume": "38",
"container-title": "IEEE Signal Processing Magazine"
}
Claims
-
The DCASE challenge annually offers several tasks for public benchmarking of methods.
"The international evaluation challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) is an important community effort that offers annually several tasks allowing public benchmarking of methods."
-
Sound event detection aims to recognize what is happening in an audio signal and when it is happening.
"The goal of automatic sound event detection (SED) methods is to recognize what is happening in an audio signal and when it is happening."
-
Natural environments are polyphonic, with multiple sounds active at once, and there are no predefined rules on how sound events co-occur.
"Natural environments are polyphonic, meaning that multiple sounds may be active at the same time. ... For sound events, there are no predefined rules on how sounds can co-occur"
Available in