{"id":"https://openalex.org/W4408355445","doi":"https://doi.org/10.1109/icassp49660.2025.10889474","title":"Unsupervised Domain Adaptation for Music Transcription: Exploiting Cross-Version Consistency","display_name":"Unsupervised Domain Adaptation for Music Transcription: Exploiting Cross-Version Consistency","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355445","doi":"https://doi.org/10.1109/icassp49660.2025.10889474"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100640853","display_name":"Lele Liu","orcid":"https://orcid.org/0000-0001-6967-5477"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lele Liu","raw_affiliation_strings":["University of Würzburg,Computational Humanities, Center for Artificial Intelligence and Data Science (CAIDAS),Würzburg,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Würzburg,Computational Humanities, Center for Artificial Intelligence and Data Science (CAIDAS),Würzburg,Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035848608","display_name":"Ch. Wei\u00df","orcid":"https://orcid.org/0000-0003-2143-4679"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christof Wei\u00df","raw_affiliation_strings":["University of Würzburg,Computational Humanities, Center for Artificial Intelligence and Data Science (CAIDAS),Würzburg,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Würzburg,Computational Humanities, Center for Artificial Intelligence and Data Science (CAIDAS),Würzburg,Germany","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9839000105857849,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9713000059127808,"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/domain-adaptation","display_name":"Domain adaptation","score":0.7202082276344299},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6761677265167236},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5679295659065247},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.47734907269477844},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.45511630177497864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36681875586509705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3397839665412903},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10450795292854309},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.07276853919029236}],"concepts":[{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.7202082276344299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6761677265167236},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5679295659065247},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.47734907269477844},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.45511630177497864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36681875586509705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3397839665412903},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10450795292854309},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.07276853919029236},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889474","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1979654135","https://openalex.org/W2096482524","https://openalex.org/W2478454054","https://openalex.org/W2560254426","https://openalex.org/W2605488490","https://openalex.org/W2786808285","https://openalex.org/W2798658180","https://openalex.org/W2906214917","https://openalex.org/W2963045359","https://openalex.org/W2998490864","https://openalex.org/W3035831564","https://openalex.org/W3160132431","https://openalex.org/W3162528130","https://openalex.org/W3197905771","https://openalex.org/W3209419355","https://openalex.org/W4285215832","https://openalex.org/W4292198371","https://openalex.org/W4292826157","https://openalex.org/W4320036972","https://openalex.org/W4323545743","https://openalex.org/W4387943290","https://openalex.org/W6730401039","https://openalex.org/W6745851314","https://openalex.org/W6753511437","https://openalex.org/W6755182157","https://openalex.org/W6757817989","https://openalex.org/W6759107158","https://openalex.org/W6803088475","https://openalex.org/W6854061045"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1526712007","https://openalex.org/W1533421371","https://openalex.org/W1603736412","https://openalex.org/W2003050223","https://openalex.org/W4394775207","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"With":[0],"the":[1,11,56,68,73,96,101,104,122,136,157,162,166,179,195,210],"omnipresence":[2],"of":[3,13,19,135,165],"deep":[4],"learning":[5],"approaches":[6],"in":[7,88],"modern":[8],"signal":[9],"processing,":[10],"generalization":[12],"models":[14],"to":[15,27,77,94,177,187,201],"unseen":[16],"domains":[17],"is":[18],"crucial":[20],"importance.":[21],"Various":[22],"strategies":[23],"have":[24],"been":[25],"proposed":[26,123,211],"address":[28],"such":[29],"unsupervised":[30,180],"domain":[31,58,168,181],"adaptation":[32,182],"including":[33],"reconstruction":[34,149],"autoencoders":[35],"and":[36,191],"adversarial":[37],"training.":[38],"In":[39,117],"this":[40,118,141],"paper,":[41,119],"we":[42,50,75,120,152,205],"propose":[43,76],"another":[44],"strategy":[45,124,142,155,175],"using":[46,59,132,147,209],"teacher\u2013student":[47],"learning,":[48],"where":[49],"train":[51],"a":[52,63,126,144,148],"student":[53],"model":[54,65,106],"for":[55,125,194],"target":[57,167],"pseudo-labels":[60,102],"generated":[61],"by":[62,107,113,160],"teacher":[64,105],"trained":[66],"on":[67],"source":[69],"domain.":[70],"To":[71],"improve":[72,178],"adaptation,":[74],"exploit":[78],"cross-version":[79,163],"data,":[80],"i.e.,":[81],"target-domain":[82],"data":[83],"without":[84],"labels":[85,111],"but":[86],"existing":[87],"different":[89,133],"versions,":[90],"which":[91],"are":[92],"expected":[93],"share":[95],"same":[97,137],"labels.":[98,116],"We":[99,139],"process":[100],"from":[103,183,198],"keeping":[108],"only":[109],"consistent":[110],"or":[112],"interpolating":[114],"conflicting":[115],"demonstrate":[121],"music":[127,200],"transcription":[128],"subtask":[129],"(multi-pitch":[130],"estimation)":[131],"performances":[134],"composition.":[138],"compare":[140],"with":[143,156],"baseline":[145,158],"method":[146,159],"autoencoder.":[150],"Furthermore,":[151],"combine":[153],"our":[154,174],"enforcing":[161],"consistency":[164],"predictions.":[169],"Our":[170],"results":[171],"show":[172],"that":[173],"helps":[176],"one":[184],"instrument":[185],"(piano)":[186],"other":[188],"instruments":[189],"(singing":[190],"orchestra).":[192],"Especially":[193],"difficult":[196],"transfer":[197],"piano":[199],"complex":[202],"orchestral":[203],"music,":[204],"obtain":[206],"substantial":[207],"improvements":[208],"approach.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}