{"id":"https://openalex.org/W4416798832","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249321","title":"Accuracy Improvement of Automatic Chord Recognition with Source Separation Preprocessing","display_name":"Accuracy Improvement of Automatic Chord Recognition with Source Separation Preprocessing","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798832","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249321"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5107019664","display_name":"Ayumu Mitoma","orcid":null},"institutions":[{"id":"https://openalex.org/I188815454","display_name":"Oita University","ror":"https://ror.org/01nyv7k26","country_code":"JP","type":"education","lineage":["https://openalex.org/I188815454"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ayumu Mitoma","raw_affiliation_strings":["Oita University,Oita,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oita University,Oita,Japan","institution_ids":["https://openalex.org/I188815454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044786146","display_name":"Ken\u2019ichi Furuya","orcid":"https://orcid.org/0000-0002-5407-3673"},"institutions":[{"id":"https://openalex.org/I188815454","display_name":"Oita University","ror":"https://ror.org/01nyv7k26","country_code":"JP","type":"education","lineage":["https://openalex.org/I188815454"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ken'ichi Furuya","raw_affiliation_strings":["Oita University,Oita,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oita University,Oita,Japan","institution_ids":["https://openalex.org/I188815454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I188815454"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3854461,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"288","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9782000184059143,"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":0.9782000184059143,"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":0.0017999999690800905,"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":0.0010999999940395355,"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/chord","display_name":"Chord (peer-to-peer)","score":0.8870000243186951},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.73089998960495},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5616999864578247},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.3765000104904175},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3677999973297119},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35850000381469727},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.33160001039505005}],"concepts":[{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.8870000243186951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423999905586243},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.73089998960495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.660099983215332},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5616999864578247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5199000239372253},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3698999881744385},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3677999973297119},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.3294999897480011},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C117623542","wikidata":"https://www.wikidata.org/wiki/Q621974","display_name":"Automatic target recognition","level":3,"score":0.29789999127388},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.26330000162124634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2165320163","https://openalex.org/W3095798115","https://openalex.org/W3129917041","https://openalex.org/W4372260250","https://openalex.org/W4375928773","https://openalex.org/W4385245566"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"chord":[1,57,61,77,163],"recognition":[2,58,62,78,101,169],"is":[3,92],"a":[4,60,113,117,130,142],"fundamental":[5],"research":[6],"topic":[7],"in":[8,108],"music":[9,25,96],"information":[10],"retrieval":[11,23],"(MIR)":[12],"and":[13,24,42,67,144,165],"has":[14],"been":[15,38],"applied":[16],"to":[17],"various":[18],"tasks,":[19],"including":[20],"cover":[21],"song":[22],"key":[26],"detection.":[27],"In":[28,46],"recent":[29],"years,":[30],"several":[31],"methods":[32],"based":[33,64],"on":[34,51,65,105],"deep":[35],"learning":[36],"have":[37],"proposed,":[39],"enabling":[40],"easier":[41],"more":[43,154],"accurate":[44],"recognition.":[45],"this":[47],"study,":[48],"we":[49,103,146],"focused":[50],"the":[52,76,81,100,106,135,149,167,173],"bi-directional":[53],"Transformer":[54],"for":[55,80,94],"musical":[56],"(BTC),":[59],"method":[63,118,151],"Transformers,":[66],"evaluated":[68],"its":[69],"performance.":[70],"The":[71],"experimental":[72],"results":[73],"showed":[74],"that":[75,119,148],"accuracy":[79,170],"triads":[82],"was":[83],"<tex":[84,156],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[85,157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{7":[86],"5.":[87],"5":[88],"2":[89],"\\%}$</tex>,":[90],"which":[91],"insufficient":[93],"realworld":[95],"applications.":[97],"To":[98],"improve":[99],"accuracy,":[102],"focus":[104],"differences":[107],"volume":[109,136],"between":[110],"instruments":[111,124],"within":[112],"song.":[114],"We":[115],"propose":[116],"emphasizes":[120],"sounds":[121],"from":[122],"chord-relevant":[123],"by":[125],"applying":[126],"source":[127],"separation":[128],"as":[129,141],"preprocessing":[131],"step.":[132],"By":[133],"amplifying":[134],"of":[137],"pitched":[138],"instruments,":[139],"such":[140],"piano":[143],"guitar,":[145],"confirmed":[147],"proposed":[150],"successfully":[152],"corrected":[153],"than":[155],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{2,":[158],"0":[159,160],"0}$</tex>":[161],"misrecognized":[162],"frames":[164],"improved":[166],"overall":[168],"compared":[171],"with":[172],"conventional":[174],"method.":[175]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-28T00:00:00"}