An automated pop song mashup system using drum swapping

Music mashups blend elements from two or more songs. They are extremely popular among both composers and listeners since they carry the emotional power of the original songs, plus delightful new surprises. A few automated systems have appeared on the mashup scene, but the results are often heavy-han...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Journal of the Acoustical Society of America 2023-10, Vol.154 (4_supplement), p.A288-A289
Hauptverfasser: Wu, Xinyang, Horner, Andrew
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page A289
container_issue 4_supplement
container_start_page A288
container_title The Journal of the Acoustical Society of America
container_volume 154
creator Wu, Xinyang
Horner, Andrew
description Music mashups blend elements from two or more songs. They are extremely popular among both composers and listeners since they carry the emotional power of the original songs, plus delightful new surprises. A few automated systems have appeared on the mashup scene, but the results are often heavy-handed and muddy, since they usually combine everything from both songs, and therefore, lack the nuance and clarity of hand-crafted mashups by professional composers. We propose a mashup system “Rhythm Fusion” that allows users to swap the drum track from one song into another. We use a beat-tracking algorithm to synchronize and align the songs. In our preliminary subjective tests, 10 songs were used to generate 100 combinations. Of these, 27% of the variations were rated more musically satisfying than the original. These results indicate that drum swapping alone has much promise for music mashups, and will guide our future work on swapping both drums and bass stems from different songs in automated music mashups, and eventually other components as well.
doi_str_mv 10.1121/10.0023554
format Article
fullrecord <record><control><sourceid>crossref</sourceid><recordid>TN_cdi_crossref_primary_10_1121_10_0023554</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1121_10_0023554</sourcerecordid><originalsourceid>FETCH-crossref_primary_10_1121_10_00235543</originalsourceid><addsrcrecordid>eNqVjk0KwjAUhB-iYP3ZeIKshepL2tR2KaJ4APcl2FQrpg15DdLbm4IXcPXNDLP4ADYcd5wLvg9EFImU6QQiLgXGuRTpFCJE5HFaZNkcFkSvUGWeFBEcji1Tvu-M6nXFbGcZde2DGUVPH_JAvTbMUxO2ynnD6KOsDW0Fs1q9Sa9_XML2cr6drvHddURO16V1jVFuKDmWo9rIn1ry1_kL7Q89xA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>An automated pop song mashup system using drum swapping</title><source>AIP Journals Complete</source><source>Alma/SFX Local Collection</source><source>AIP Acoustical Society of America</source><creator>Wu, Xinyang ; Horner, Andrew</creator><creatorcontrib>Wu, Xinyang ; Horner, Andrew</creatorcontrib><description>Music mashups blend elements from two or more songs. They are extremely popular among both composers and listeners since they carry the emotional power of the original songs, plus delightful new surprises. A few automated systems have appeared on the mashup scene, but the results are often heavy-handed and muddy, since they usually combine everything from both songs, and therefore, lack the nuance and clarity of hand-crafted mashups by professional composers. We propose a mashup system “Rhythm Fusion” that allows users to swap the drum track from one song into another. We use a beat-tracking algorithm to synchronize and align the songs. In our preliminary subjective tests, 10 songs were used to generate 100 combinations. Of these, 27% of the variations were rated more musically satisfying than the original. These results indicate that drum swapping alone has much promise for music mashups, and will guide our future work on swapping both drums and bass stems from different songs in automated music mashups, and eventually other components as well.</description><identifier>ISSN: 0001-4966</identifier><identifier>EISSN: 1520-8524</identifier><identifier>DOI: 10.1121/10.0023554</identifier><language>eng</language><ispartof>The Journal of the Acoustical Society of America, 2023-10, Vol.154 (4_supplement), p.A288-A289</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>207,208,314,780,784,27923,27924</link.rule.ids></links><search><creatorcontrib>Wu, Xinyang</creatorcontrib><creatorcontrib>Horner, Andrew</creatorcontrib><title>An automated pop song mashup system using drum swapping</title><title>The Journal of the Acoustical Society of America</title><description>Music mashups blend elements from two or more songs. They are extremely popular among both composers and listeners since they carry the emotional power of the original songs, plus delightful new surprises. A few automated systems have appeared on the mashup scene, but the results are often heavy-handed and muddy, since they usually combine everything from both songs, and therefore, lack the nuance and clarity of hand-crafted mashups by professional composers. We propose a mashup system “Rhythm Fusion” that allows users to swap the drum track from one song into another. We use a beat-tracking algorithm to synchronize and align the songs. In our preliminary subjective tests, 10 songs were used to generate 100 combinations. Of these, 27% of the variations were rated more musically satisfying than the original. These results indicate that drum swapping alone has much promise for music mashups, and will guide our future work on swapping both drums and bass stems from different songs in automated music mashups, and eventually other components as well.</description><issn>0001-4966</issn><issn>1520-8524</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><recordid>eNqVjk0KwjAUhB-iYP3ZeIKshepL2tR2KaJ4APcl2FQrpg15DdLbm4IXcPXNDLP4ADYcd5wLvg9EFImU6QQiLgXGuRTpFCJE5HFaZNkcFkSvUGWeFBEcji1Tvu-M6nXFbGcZde2DGUVPH_JAvTbMUxO2ynnD6KOsDW0Fs1q9Sa9_XML2cr6drvHddURO16V1jVFuKDmWo9rIn1ry1_kL7Q89xA</recordid><startdate>20231001</startdate><enddate>20231001</enddate><creator>Wu, Xinyang</creator><creator>Horner, Andrew</creator><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20231001</creationdate><title>An automated pop song mashup system using drum swapping</title><author>Wu, Xinyang ; Horner, Andrew</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-crossref_primary_10_1121_10_00235543</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wu, Xinyang</creatorcontrib><creatorcontrib>Horner, Andrew</creatorcontrib><collection>CrossRef</collection><jtitle>The Journal of the Acoustical Society of America</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wu, Xinyang</au><au>Horner, Andrew</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An automated pop song mashup system using drum swapping</atitle><jtitle>The Journal of the Acoustical Society of America</jtitle><date>2023-10-01</date><risdate>2023</risdate><volume>154</volume><issue>4_supplement</issue><spage>A288</spage><epage>A289</epage><pages>A288-A289</pages><issn>0001-4966</issn><eissn>1520-8524</eissn><abstract>Music mashups blend elements from two or more songs. They are extremely popular among both composers and listeners since they carry the emotional power of the original songs, plus delightful new surprises. A few automated systems have appeared on the mashup scene, but the results are often heavy-handed and muddy, since they usually combine everything from both songs, and therefore, lack the nuance and clarity of hand-crafted mashups by professional composers. We propose a mashup system “Rhythm Fusion” that allows users to swap the drum track from one song into another. We use a beat-tracking algorithm to synchronize and align the songs. In our preliminary subjective tests, 10 songs were used to generate 100 combinations. Of these, 27% of the variations were rated more musically satisfying than the original. These results indicate that drum swapping alone has much promise for music mashups, and will guide our future work on swapping both drums and bass stems from different songs in automated music mashups, and eventually other components as well.</abstract><doi>10.1121/10.0023554</doi></addata></record>
fulltext fulltext
identifier ISSN: 0001-4966
ispartof The Journal of the Acoustical Society of America, 2023-10, Vol.154 (4_supplement), p.A288-A289
issn 0001-4966
1520-8524
language eng
recordid cdi_crossref_primary_10_1121_10_0023554
source AIP Journals Complete; Alma/SFX Local Collection; AIP Acoustical Society of America
title An automated pop song mashup system using drum swapping
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-09T08%3A20%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20automated%20pop%20song%20mashup%20system%20using%20drum%20swapping&rft.jtitle=The%20Journal%20of%20the%20Acoustical%20Society%20of%20America&rft.au=Wu,%20Xinyang&rft.date=2023-10-01&rft.volume=154&rft.issue=4_supplement&rft.spage=A288&rft.epage=A289&rft.pages=A288-A289&rft.issn=0001-4966&rft.eissn=1520-8524&rft_id=info:doi/10.1121/10.0023554&rft_dat=%3Ccrossref%3E10_1121_10_0023554%3C/crossref%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true