{"id":"https://openalex.org/W4388820346","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317292","title":"Exploring Isolated Musical Notes as Pre-training Data for Predominant Instrument Recognition in Polyphonic Music","display_name":"Exploring Isolated Musical Notes as Pre-training Data for Predominant Instrument Recognition in Polyphonic Music","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820346","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317292"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110993210","display_name":"Lifan Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lifan Zhong","raw_affiliation_strings":["The University of Tokyo,Graduate School of Engineering,Japan","Graduate School of Engineering, The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Engineering,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Engineering, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["The University of Tokyo,Graduate School of Engineering,Japan","Graduate School of Engineering, The University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Engineering,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Engineering, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2312","last_page":"2319"},"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":0.9976999759674072,"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":0.9958999752998352,"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/polyphony","display_name":"Polyphony","score":0.9361786842346191},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.7317876815795898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7072852849960327},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6067389845848083},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.535123348236084},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.514982283115387},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4508422017097473},{"id":"https://openalex.org/keywords/meaning","display_name":"Meaning (existential)","score":0.41901981830596924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4156896770000458},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34204769134521484},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3389381766319275},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09243807196617126},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08721289038658142},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.06563106179237366}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.9361786842346191},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.7317876815795898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7072852849960327},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6067389845848083},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.535123348236084},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.514982283115387},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4508422017097473},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.41901981830596924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4156896770000458},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34204769134521484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3389381766319275},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09243807196617126},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08721289038658142},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.06563106179237366},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W875533737","https://openalex.org/W1522301498","https://openalex.org/W1569206690","https://openalex.org/W1590102137","https://openalex.org/W2031767620","https://openalex.org/W2053463056","https://openalex.org/W2110975186","https://openalex.org/W2113539812","https://openalex.org/W2134277037","https://openalex.org/W2158691456","https://openalex.org/W2183341477","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2410860376","https://openalex.org/W2604509013","https://openalex.org/W2606176153","https://openalex.org/W2765407302","https://openalex.org/W2768188490","https://openalex.org/W2782669246","https://openalex.org/W2888806961","https://openalex.org/W2903539539","https://openalex.org/W2963077989","https://openalex.org/W2963727650","https://openalex.org/W2964052309","https://openalex.org/W2964096688","https://openalex.org/W2990912900","https://openalex.org/W3004440566","https://openalex.org/W3098670224","https://openalex.org/W3160793127","https://openalex.org/W4205137627","https://openalex.org/W4280618035","https://openalex.org/W4287694193","https://openalex.org/W6624135329","https://openalex.org/W6631190155","https://openalex.org/W6634144402","https://openalex.org/W6635274319","https://openalex.org/W6676291810","https://openalex.org/W6736723571","https://openalex.org/W6745136726","https://openalex.org/W6745930336","https://openalex.org/W6756873980","https://openalex.org/W6766336120","https://openalex.org/W6781762595"],"related_works":["https://openalex.org/W2727800297","https://openalex.org/W2797744129","https://openalex.org/W2415999852","https://openalex.org/W2030575009","https://openalex.org/W2991141425","https://openalex.org/W2002620859","https://openalex.org/W2591743215","https://openalex.org/W4390012055","https://openalex.org/W7350038","https://openalex.org/W126167045"],"abstract_inverted_index":{"With":[0],"the":[1,13,85,88,100,115,154],"growing":[2],"amount":[3,75],"of":[4,12,30,76,139,144],"musical":[5,42,78,105,121],"data":[6,79,95,106],"available,":[7],"automatic":[8,28],"instrument":[9,54],"recognition,":[10],"one":[11],"essential":[14],"problems":[15],"in":[16],"Music":[17],"Information":[18],"Retrieval":[19],"(MIR),":[20],"is":[21],"drawing":[22],"more":[23,25],"and":[24,68,82,107,141,148],"attention.":[26],"While":[27],"recognition":[29,55],"single":[31],"instruments":[32],"has":[33],"been":[34],"well-studied,":[35],"it":[36],"remains":[37],"challenging":[38],"for":[39,57,80,87],"polyphonic,":[40],"multi-instrument":[41,59],"recordings.":[43,127],"This":[44],"work":[45],"presents":[46],"our":[47,63,112,132],"efforts":[48],"toward":[49],"building":[50],"a":[51,66,73,119,136,165],"robust":[52],"end-to-end":[53,157],"system":[56],"polyphonic":[58,89,120],"music.":[60,109],"We":[61,110],"train":[62],"model":[64,86,134],"using":[65],"pre-training":[67,81],"fine-tuning":[69],"approach:":[70],"we":[71,93,160],"use":[72],"large":[74],"monophonic":[77,104],"subsequently":[83],"fine-tune":[84],"ensemble.":[90],"In":[91],"pre-training,":[92],"apply":[94],"augmentation":[96],"techniques":[97],"to":[98,163],"alleviate":[99],"domain":[101],"gap":[102],"between":[103],"real-world":[108],"evaluate":[111],"method":[113],"on":[114],"IRMAS":[116],"testing":[117],"data,":[118],"dataset":[122],"comprising":[123],"professionally-produced":[124],"commercial":[125],"music":[126],"Experimental":[128],"results":[129],"show":[130],"that":[131],"best":[133],"achieves":[135],"micro":[137],"F1-score":[138],"0.674":[140],"an":[142],"LRAP":[143],"0.814,":[145],"meaning":[146],"10.9%":[147],"8.9%":[149],"relative":[150],"improvement":[151],"compared":[152],"with":[153,171],"previous":[155],"state-of-the-art":[156],"approach.":[158],"Also,":[159],"are":[161],"able":[162],"build":[164],"lightweight":[166],"model,":[167],"achieving":[168],"competitive":[169],"performance":[170],"only":[172],"519K":[173],"trainable":[174],"parameters.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
