{"id":"https://openalex.org/W3158877740","doi":"https://doi.org/10.1017/s1351324921000024","title":"Lyrics segmentation via bimodal text\u2013audio representation","display_name":"Lyrics segmentation via bimodal text\u2013audio representation","publication_year":2021,"publication_date":"2021-05-05","ids":{"openalex":"https://openalex.org/W3158877740","doi":"https://doi.org/10.1017/s1351324921000024","mag":"3158877740"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324921000024","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324921000024","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03295581","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000252838","display_name":"Michael J. Fell","orcid":"https://orcid.org/0000-0003-2764-7464"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Michael Fell","raw_affiliation_strings":["Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, Inria, I3S, France","Web-Instrumented Man-Machine Interactions, Communities and Semantics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, Inria, I3S, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Web-Instrumented Man-Machine Interactions, Communities and Semantics","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082557743","display_name":"Yaroslav Nechaev","orcid":"https://orcid.org/0000-0003-2539-191X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yaroslav Nechaev","raw_affiliation_strings":["Amazon, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062693009","display_name":"Gabriel Meseguer-Brocal","orcid":"https://orcid.org/0000-0002-5232-8628"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gabriel Meseguer-Brocal","raw_affiliation_strings":["Ircam Lab, CNRS, Sorbonne Universit\u00e9, Paris, France","Centre National de la Recherche Scientifique","Institut de Recherche et Coordination Acoustique/Musique","Sorbonne Universite\u0301"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ircam Lab, CNRS, Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Centre National de la Recherche Scientifique","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Institut de Recherche et Coordination Acoustique/Musique","institution_ids":["https://openalex.org/I35345632"]},{"raw_affiliation_string":"Sorbonne Universite\u0301","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049137879","display_name":"Elena Cabrio","orcid":"https://orcid.org/0000-0001-9374-7872"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Elena Cabrio","raw_affiliation_strings":["Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, Inria, I3S, France","Web-Instrumented Man-Machine Interactions, Communities and Semantics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, Inria, I3S, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Web-Instrumented Man-Machine Interactions, Communities and Semantics","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044946197","display_name":"Fabien Gandon","orcid":"https://orcid.org/0000-0003-0543-1232"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabien Gandon","raw_affiliation_strings":["Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, Inria, I3S, France","Web-Instrumented Man-Machine Interactions, Communities and Semantics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, Inria, I3S, France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Web-Instrumented Man-Machine Interactions, Communities and Semantics","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","Laboratoire Traitement et Communication de l'Information"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]},{"raw_affiliation_string":"Laboratoire Traitement et Communication de l'Information","institution_ids":["https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5000252838"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I1326498283"],"apc_list":null,"apc_paid":null,"fwci":0.4486,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58742086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"28","issue":"3","first_page":"317","last_page":"336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/lyrics","display_name":"Lyrics","score":0.9794323444366455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.824093222618103},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6773815155029297},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.557741105556488},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5507425665855408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5177571177482605},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4751013517379761},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07790055871009827},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.06183275580406189}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9794323444366455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.824093222618103},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6773815155029297},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.557741105556488},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5507425665855408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5177571177482605},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4751013517379761},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07790055871009827},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.06183275580406189},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1017/s1351324921000024","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324921000024","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-03295581v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03295581","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Natural Language Engineering, 2022, 28 (3), pp.317 - 336. ⟨10.1017/S1351324921000024⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03295581v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03295581","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Natural Language Engineering, 2022, 28 (3), pp.317 - 336. ⟨10.1017/S1351324921000024⟩","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6388069114","display_name":"Web Audio and Semantic Aggregated in the Browser for Indexation","funder_award_id":"ANR-16-CE23-0017","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W307744830","https://openalex.org/W1520449809","https://openalex.org/W1647671624","https://openalex.org/W1682639223","https://openalex.org/W2059363583","https://openalex.org/W2059412221","https://openalex.org/W2085830989","https://openalex.org/W2139760786","https://openalex.org/W2148154194","https://openalex.org/W2153189457","https://openalex.org/W2160331326","https://openalex.org/W2191779130","https://openalex.org/W2250539671","https://openalex.org/W2294451090","https://openalex.org/W2314762915","https://openalex.org/W2557283755","https://openalex.org/W2574634960","https://openalex.org/W2612690371","https://openalex.org/W2740560081","https://openalex.org/W2872458424","https://openalex.org/W2903006902","https://openalex.org/W2963341956","https://openalex.org/W2999282340","https://openalex.org/W6610743868","https://openalex.org/W6631166905","https://openalex.org/W6636915900","https://openalex.org/W6637621081"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W4310670065","https://openalex.org/W634160686","https://openalex.org/W2597614303","https://openalex.org/W3214861561","https://openalex.org/W2389838651","https://openalex.org/W437317580","https://openalex.org/W2352995288","https://openalex.org/W2365365224","https://openalex.org/W1532663766"],"abstract_inverted_index":{"Abstract":[0],"Song":[1],"lyrics":[2,13,52,111,119,126],"contain":[3],"repeated":[4],"patterns":[5],"that":[6,47,100,113,159],"have":[7],"been":[8],"proven":[9],"to":[10,49,64,92,167],"facilitate":[11],"automated":[12],"segmentation,":[14],"with":[15,61],"the":[16,21,51,71,87,93,96,101,110,123,142,145,150,160,172],"final":[17],"goal":[18],"of":[19,27,68,95,109,131,138,144,154],"detecting":[20],"building":[22],"blocks":[23],"(e.g.,":[24],"chorus,":[25],"verse)":[26],"a":[28,41,83,129],"song":[29,88],"text.":[30],"Our":[31],"contribution":[32],"in":[33,70],"this":[34],"article":[35],"is":[36,90,116],"twofold.":[37],"First,":[38],"we":[39,98,134,157],"introduce":[40],"convolutional":[42],"neural":[43],"network":[44],"(CNN)-based":[45],"model":[46],"learns":[48],"segment":[50],"based":[53,75],"on":[54,76,128,141],"their":[55],"repetitive":[56],"text":[57,89,102],"structure.":[58],"We":[59],"experiment":[60],"novel":[62,84],"features":[63,163],"reveal":[65],"different":[66],"kinds":[67],"repetitions":[69],"lyrics,":[72,133],"for":[73,118],"instance":[74],"phonetical":[77],"and":[78,103,112],"syntactical":[79],"properties.":[80],"Second,":[81],"using":[82],"corpus":[85],"where":[86],"synchronized":[91,151],"audio":[94,104,162],"song,":[97],"show":[99,158],"modalities":[105],"capture":[106],"complementary":[107],"structure":[108],"combining":[114],"both":[115],"beneficial":[117],"segmentation":[120,127,165],"performance.":[121],"For":[122],"purely":[124,173],"text-based":[125,174],"dataset":[130,153],"103k":[132],"achieve":[135],"an":[136],"F-score":[137],"67.4%,":[139],"improving":[140],"state":[143],"art":[146],"(59.2%":[147],"F-score).":[148],"On":[149],"text\u2013audio":[152],"4.8k":[155],"songs,":[156],"additional":[161],"improve":[164],"performance":[166],"75.3%":[168],"F-score,":[169],"significantly":[170],"outperforming":[171],"approaches.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}