{"id":"https://openalex.org/W4392909877","doi":"https://doi.org/10.1109/icassp48485.2024.10447561","title":"MIR-MLPop: A Multilingual Pop Music Dataset with Time-Aligned Lyrics and Audio","display_name":"MIR-MLPop: A Multilingual Pop Music Dataset with Time-Aligned Lyrics and Audio","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909877","doi":"https://doi.org/10.1109/icassp48485.2024.10447561"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016862479","display_name":"Jun-You Wang","orcid":"https://orcid.org/0000-0002-9119-9259"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jun-You Wang","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016475945","display_name":"Chung-Che Wang","orcid":"https://orcid.org/0000-0002-1414-9848"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Che Wang","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113099719","display_name":"Chon-In Leong","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chon-In Leong","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073451247","display_name":"Jyh\u2010Shing Roger Jang","orcid":"https://orcid.org/0000-0002-7319-9095"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Shing Roger Jang","raw_affiliation_strings":["National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.2995,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45958686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1366","last_page":"1370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9621999859809875,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.9584012031555176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.648874044418335},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.572443425655365},{"id":"https://openalex.org/keywords/popular-music","display_name":"Popular music","score":0.42984020709991455},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.19787487387657166},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.11726543307304382},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.06206253170967102}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9584012031555176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.648874044418335},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.572443425655365},{"id":"https://openalex.org/C114611597","wikidata":"https://www.wikidata.org/wiki/Q373342","display_name":"Popular music","level":2,"score":0.42984020709991455},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.19787487387657166},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.11726543307304382},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.06206253170967102}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322108","display_name":"Ministry of Science and Technology","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2059239154","https://openalex.org/W2124539664","https://openalex.org/W2134387846","https://openalex.org/W2142384583","https://openalex.org/W2760576352","https://openalex.org/W2935701729","https://openalex.org/W2972856300","https://openalex.org/W3015315843","https://openalex.org/W3036601975","https://openalex.org/W3090751054","https://openalex.org/W3160569418","https://openalex.org/W3213029956","https://openalex.org/W4223646224","https://openalex.org/W4224931246","https://openalex.org/W4285819380","https://openalex.org/W4311000453","https://openalex.org/W4372260250","https://openalex.org/W4372260429","https://openalex.org/W4391021537","https://openalex.org/W6756588447","https://openalex.org/W6757122045","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6786603260","https://openalex.org/W6799375923","https://openalex.org/W6799484589","https://openalex.org/W6804030475","https://openalex.org/W6810177958","https://openalex.org/W6847363464","https://openalex.org/W6854460176"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2067430219","https://openalex.org/W4379348330","https://openalex.org/W2964472689","https://openalex.org/W2263813420","https://openalex.org/W2062196734","https://openalex.org/W2491013962","https://openalex.org/W2762717821","https://openalex.org/W2080906825","https://openalex.org/W1538363195"],"abstract_inverted_index":{"We":[0],"introduce":[1],"MIR-MLPop,":[2],"a":[3],"publicly":[4],"available":[5],"multilingual":[6],"pop":[7,25],"music":[8,26],"dataset":[9,22,57],"designed":[10],"for":[11,58,82,91,134],"automatic":[12],"lyrics":[13,16,38,76,79,130],"transcription":[14,77,131],"and":[15,31,42,60,78,132],"alignment":[17,80,133],"in":[18,28,129],"polyphonic":[19],"music.":[20],"The":[21],"comprises":[23],"90":[24],"tracks":[27],"Mandarin,":[29],"Cantonese,":[30],"Taiwanese":[32,61],"Hokkien,":[33],"with":[34,39],"manually":[35],"annotated":[36],"time-aligned":[37],"both":[40,92],"characters":[41],"pronunciation":[43],"labels.":[44],"To":[45],"the":[46,53,64,67,72,87,99,118,126],"best":[47],"of":[48],"our":[49],"knowledge,":[50],"this":[51],"is":[52],"first":[54],"ever":[55],"singing":[56],"Cantonese":[59],"Hokkien.":[62],"In":[63],"experiments,":[65],"using":[66],"pretrained":[68,143],"Whisper":[69,113],"model":[70],"as":[71],"backbone,":[73],"we":[74],"develop":[75],"models":[81,102],"all":[83],"three":[84],"languages.":[85,100],"Overall,":[86],"results":[88],"are":[89],"promising":[90],"tasks,":[93],"but":[94],"show":[95],"clear":[96],"differences":[97],"among":[98],"Our":[101],"perform":[103],"significantly":[104],"better":[105],"on":[106,117],"languages":[107,136],"that":[108,137],"have":[109,138],"been":[110,140],"seen":[111],"by":[112,121,142],"during":[114],"pretraining":[115],"than":[116],"language":[119],"unseen":[120],"Whisper.":[122],"This":[123],"finding":[124],"highlights":[125],"potential":[127],"challenge":[128],"low-resource":[135],"not":[139],"covered":[141],"speech":[144],"models.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
