{"id":"https://openalex.org/W4224944643","doi":"https://doi.org/10.1109/icassp43922.2022.9747252","title":"To Catch A Chorus, Verse, Intro, or Anything Else: Analyzing a Song with Structural Functions","display_name":"To Catch A Chorus, Verse, Intro, or Anything Else: Analyzing a Song with Structural Functions","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224944643","doi":"https://doi.org/10.1109/icassp43922.2022.9747252"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747252","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97459/2/Smith%20To%20Catch%20A%20Chorus%202022%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":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["ByteDance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005504900","display_name":"Yun-Ning Hung","orcid":"https://orcid.org/0000-0002-7242-6903"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun-Ning Hung","raw_affiliation_strings":["Georgia Institute of Technology,Center for Music Technology,Atlanta,GA,USA","Center for Music Technology, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Center for Music Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Center for Music Technology, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"416","last_page":"420"},"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":0.9950000047683716,"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/T10860","display_name":"Speech and Audio Processing","score":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/chorus","display_name":"Chorus","score":0.9291545748710632},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7541048526763916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5555595755577087},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.465517520904541},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43953779339790344},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4265669882297516}],"concepts":[{"id":"https://openalex.org/C2780832652","wikidata":"https://www.wikidata.org/wiki/Q5105266","display_name":"Chorus","level":2,"score":0.9291545748710632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541048526763916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5555595755577087},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.465517520904541},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43953779339790344},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4265669882297516},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747252","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97459","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97459","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97459/2/Smith%20To%20Catch%20A%20Chorus%202022%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:123456789/97459","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97459","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97459/2/Smith%20To%20Catch%20A%20Chorus%202022%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":[{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4224944643.pdf"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W397515860","https://openalex.org/W1519655822","https://openalex.org/W1522301498","https://openalex.org/W1978421240","https://openalex.org/W2110681820","https://openalex.org/W2130976598","https://openalex.org/W2163643934","https://openalex.org/W2168249484","https://openalex.org/W2293125622","https://openalex.org/W2399621629","https://openalex.org/W2400508010","https://openalex.org/W2404620398","https://openalex.org/W2405639812","https://openalex.org/W2406676415","https://openalex.org/W2407685581","https://openalex.org/W2576859507","https://openalex.org/W2675366439","https://openalex.org/W2896457183","https://openalex.org/W2913868053","https://openalex.org/W2919624000","https://openalex.org/W2963202769","https://openalex.org/W2990861008","https://openalex.org/W3015289235","https://openalex.org/W3029858316","https://openalex.org/W3112091658","https://openalex.org/W3145867403","https://openalex.org/W3162686331","https://openalex.org/W3173187964","https://openalex.org/W3207444892","https://openalex.org/W3214581616","https://openalex.org/W4205417752","https://openalex.org/W4224918587","https://openalex.org/W4286850225","https://openalex.org/W4286901894","https://openalex.org/W4385245566","https://openalex.org/W6613661022","https://openalex.org/W6631117800","https://openalex.org/W6631190155","https://openalex.org/W6697165675","https://openalex.org/W6712738210","https://openalex.org/W6712946787","https://openalex.org/W6713016031","https://openalex.org/W6713840425","https://openalex.org/W6714030504","https://openalex.org/W6714143802","https://openalex.org/W6732421603","https://openalex.org/W6739901393","https://openalex.org/W6739918249","https://openalex.org/W6755207826","https://openalex.org/W6760601182","https://openalex.org/W6770646036","https://openalex.org/W6778572914","https://openalex.org/W6784730479","https://openalex.org/W6793531982","https://openalex.org/W6796369303","https://openalex.org/W6803003856","https://openalex.org/W6803752119","https://openalex.org/W6804109046","https://openalex.org/W6811445250"],"related_works":["https://openalex.org/W2809745188","https://openalex.org/W2349772854","https://openalex.org/W2494818933","https://openalex.org/W3152157429","https://openalex.org/W2364547139","https://openalex.org/W2475648064","https://openalex.org/W2139934687","https://openalex.org/W2357558268","https://openalex.org/W3211508905","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Conventional":[0],"music":[1],"structure":[2],"analysis":[3],"algorithms":[4],"aim":[5],"to":[6,13,50,88,98],"divide":[7],"a":[8,45,67,73,100],"song":[9],"into":[10],"segments":[11],"and":[12,22,63,83,85,133,136,147,153],"group":[14],"them":[15],"with":[16,110],"abstract":[17],"labels":[18,55],"(e.g.,":[19,32],"\u2018A\u2019,":[20],"\u2018B\u2019,":[21],"\u2018C\u2019).":[23],"However,":[24],"explicitly":[25],"identifying":[26],"the":[27,127,130,141],"function":[28,68],"of":[29,69,129],"each":[30],"segment":[31],"\u2018verse\u2019":[33],"or":[34],"\u2018chorus\u2019)":[35],"is":[36],"rarely":[37],"attempted,":[38],"but":[39],"has":[40],"many":[41],"applications.":[42],"We":[43,71,95],"introduce":[44],"multi-task":[46],"deep":[47],"learning":[48],"framework":[49],"model":[51,132],"these":[52],"structural":[53],"semantic":[54],"directly":[56],"from":[57,91],"audio":[58],"by":[59],"estimating":[60],"\"verseness,\"":[61],"\"chorusness,\"":[62],"so":[64],"forth,":[65],"as":[66],"time.":[70],"propose":[72,97],"7-class":[74],"taxonomy":[75],"(i.e.,":[76],"intro,":[77],"verse,":[78],"chorus,":[79],"bridge,":[80],"outro,":[81],"instrumental,":[82],"silence)":[84],"provide":[86],"rules":[87],"consolidate":[89],"annotations":[90],"four":[92,122],"disparate":[93],"datasets.":[94],"also":[96],"use":[99],"spectral-temporal":[101],"Transformer-based":[102],"model,":[103],"called":[104],"SpecTNT,":[105],"which":[106],"can":[107],"be":[108],"trained":[109],"an":[111],"additional":[112],"connectionist":[113],"temporal":[114],"localization":[115],"(CTL)":[116],"loss.":[117],"In":[118],"cross-dataset":[119],"evaluations":[120],"using":[121],"public":[123],"datasets,":[124],"we":[125],"demonstrate":[126],"effectiveness":[128],"SpecTNT":[131],"CTL":[134],"loss,":[135],"obtain":[137],"strong":[138],"results":[139],"overall:":[140],"proposed":[142],"system":[143],"outperforms":[144],"state-of-the-art":[145],"chorus-detection":[146],"boundary-detection":[148],"methods":[149],"at":[150],"detecting":[151],"choruses":[152],"boundaries,":[154],"respectively.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}