{"id":"https://openalex.org/W3162686331","doi":"https://doi.org/10.1109/icassp39728.2021.9413773","title":"Supervised Chorus Detection for Popular Music Using Convolutional Neural Network and Multi-Task Learning","display_name":"Supervised Chorus Detection for Popular Music Using Convolutional Neural Network and Multi-Task Learning","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162686331","doi":"https://doi.org/10.1109/icassp39728.2021.9413773","mag":"3162686331"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97460/2/Smith%20Supervised%20Chorus%20Detection%202021%20Accepted.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004426624","display_name":"Jordan B. L. Smith","orcid":"https://orcid.org/0000-0002-0316-1235"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jordan B.L. Smith","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046063537","display_name":"Jitong Chen","orcid":"https://orcid.org/0000-0001-6084-043X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jitong Chen","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104098658","display_name":"Xuchen Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuchen Song","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101664515","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0009-0005-3508-3736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5065288078"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3888,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.81079093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"566","last_page":"570"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chorus","display_name":"Chorus","score":0.8919250965118408},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8052056431770325},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7256051301956177},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6160839796066284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5985285043716431},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.576617419719696},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.551845908164978},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47655656933784485},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4689951241016388},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.44592347741127014},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4441833198070526},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4383639395236969},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.437668114900589},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4292258620262146},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07183817028999329}],"concepts":[{"id":"https://openalex.org/C2780832652","wikidata":"https://www.wikidata.org/wiki/Q5105266","display_name":"Chorus","level":2,"score":0.8919250965118408},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8052056431770325},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7256051301956177},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6160839796066284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985285043716431},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.576617419719696},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.551845908164978},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47655656933784485},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4689951241016388},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.44592347741127014},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4441833198070526},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4383639395236969},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.437668114900589},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4292258620262146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07183817028999329},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97460","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97460","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97460/2/Smith%20Supervised%20Chorus%20Detection%202021%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97460","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97460","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97460/2/Smith%20Supervised%20Chorus%20Detection%202021%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3162686331.pdf","grobid_xml":"https://content.openalex.org/works/W3162686331.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W78743328","https://openalex.org/W1500744329","https://openalex.org/W1994164876","https://openalex.org/W2020625454","https://openalex.org/W2051307814","https://openalex.org/W2110681820","https://openalex.org/W2123603018","https://openalex.org/W2123991323","https://openalex.org/W2130976598","https://openalex.org/W2134679199","https://openalex.org/W2142575067","https://openalex.org/W2191779130","https://openalex.org/W2207975468","https://openalex.org/W2281030185","https://openalex.org/W2293125622","https://openalex.org/W2397144118","https://openalex.org/W2404620398","https://openalex.org/W2405639812","https://openalex.org/W2406676415","https://openalex.org/W2576859507","https://openalex.org/W2767858146","https://openalex.org/W2939929812","https://openalex.org/W2962813390","https://openalex.org/W2990861008","https://openalex.org/W3102163718","https://openalex.org/W3185286209","https://openalex.org/W6603169765","https://openalex.org/W6697165675","https://openalex.org/W6712946787","https://openalex.org/W6713840425","https://openalex.org/W6714143802","https://openalex.org/W6732421603","https://openalex.org/W6745878906","https://openalex.org/W6770646036","https://openalex.org/W6785865077","https://openalex.org/W6798020702","https://openalex.org/W6968595903"],"related_works":["https://openalex.org/W2809745188","https://openalex.org/W2494818933","https://openalex.org/W2475648064","https://openalex.org/W2349772854","https://openalex.org/W3152157429","https://openalex.org/W2364547139","https://openalex.org/W2139934687","https://openalex.org/W2357558268","https://openalex.org/W3211508905","https://openalex.org/W3202613528"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,51,56,71,86,113],"novel":[4],"supervised":[5],"approach":[6,127],"to":[7,17,26,33,49,99,112],"detecting":[8],"the":[9,40,76,78,81,94],"chorus":[10,95],"segments":[11],"in":[12],"popular":[13],"music.":[14],"Traditional":[15],"approaches":[16],"this":[18],"task":[19],"are":[20],"mostly":[21],"unsupervised,":[22],"with":[23,55],"pipelines":[24],"designed":[25],"target":[27],"some":[28],"quality":[29],"that":[30,89],"is":[31],"assumed":[32],"define":[34],"\"chorusness,\"":[35],"which":[36,60],"usually":[37],"means":[38],"seeking":[39],"loudest":[41],"or":[42],"most":[43],"frequently":[44],"repeated":[45],"sections.":[46],"We":[47,83],"propose":[48,85],"use":[50],"convolutional":[52],"neural":[53],"network":[54],"multi-task":[57],"learning":[58],"objective,":[59],"simultaneously":[61],"fits":[62],"two":[63],"temporal":[64],"activation":[65],"curves:":[66],"one":[67],"indicating":[68],"\"chorusness\"":[69],"as":[70],"function":[72],"of":[73,80,115,118],"time,":[74],"and":[75,96,121,124],"other":[77,119],"location":[79],"boundaries.":[82],"also":[84],"post-processing":[87],"method":[88],"jointly":[90],"takes":[91],"into":[92],"account":[93],"boundary":[97],"predictions":[98],"produce":[100],"binary":[101],"output.":[102],"In":[103],"experiments":[104],"using":[105],"three":[106],"datasets,":[107],"we":[108],"compare":[109],"our":[110,126],"system":[111],"set":[114],"public":[116],"implementations":[117],"segmentation":[120],"chorus-detection":[122],"algorithms,":[123],"find":[125],"performs":[128],"significantly":[129],"better.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}