CITATION — REFERENCE ENTRY
Extracting Predominant Local Pulse Information From Music Recordings — IEEE Transactions on Audio, Speech, and Language Processing
- Key
- grosche2011-plp
- Authors
- Grosche, Peter; Müller, Meinard
- Issued
- 2011-8
- Type
- article-journal
- Container
- IEEE Transactions on Audio, Speech, and Language Processing
- Volume
- 19
- Issue
- 6
- Pages
- 1688-1701
Raw CSL JSON
{
"DOI": "10.1109/TASL.2010.2096216",
"page": "1688-1701",
"type": "article-journal",
"issue": "6",
"title": "Extracting Predominant Local Pulse Information From Music Recordings",
"author": [
{
"given": "Peter",
"family": "Grosche"
},
{
"given": "Meinard",
"family": "Müller"
}
],
"issued": {
"date-parts": [
[
2011,
8
]
]
},
"volume": "19",
"container-title": "IEEE Transactions on Audio, Speech, and Language Processing"
}
Claims
-
The predominant local pulse (PLP) representation fits local sinusoidal kernels to an onset representation and accumulates them, giving robust pulse information even for soft onsets and continuous tempo changes.
"The extraction of tempo and beat information from music recordings constitutes a challenging task in particular for non-percussive music with soft note onsets and time-varying tempo. [...] Our main idea is to derive for each time position a sinusoidal kernel that best explains the local periodic nature of a previously extracted note onset representation. Then we employ an overlap-add technique accumulating all these kernels over time to obtain a single function that reveals the predominant local pulse (PLP)."
Available in