{"id":"https://openalex.org/W4402980835","doi":"https://doi.org/10.1109/icme57554.2024.10688348","title":"Annotation-Free Automatic Music Transcription with Scalable Synthetic Data and Adversarial Domain Confusion","display_name":"Annotation-Free Automatic Music Transcription with Scalable Synthetic Data and Adversarial Domain Confusion","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980835","doi":"https://doi.org/10.1109/icme57554.2024.10688348"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5112848148","display_name":"Gakusei Sato","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Gakusei Sato","raw_affiliation_strings":["Sony Computer Science Laboratories,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087426444","display_name":"Taketo Akama","orcid":"https://orcid.org/0009-0007-6971-2777"},"institutions":[{"id":"https://openalex.org/I4210122684","display_name":"Sony Computer Science Laboratories","ror":"https://ror.org/02nc46417","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210122684"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taketo Akama","raw_affiliation_strings":["Sony Computer Science Laboratories,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I4210122684"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112848148"],"corresponding_institution_ids":["https://openalex.org/I4210122684"],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70483992,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9944000244140625,"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9387999773025513,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7602020502090454},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.7247728705406189},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6724228858947754},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6125283241271973},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.572136402130127},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5072088241577148},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47690415382385254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3643099069595337},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09887278079986572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602020502090454},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.7247728705406189},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6724228858947754},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6125283241271973},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.572136402130127},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5072088241577148},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47690415382385254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3643099069595337},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09887278079986572},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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":18,"referenced_works":["https://openalex.org/W1496920063","https://openalex.org/W2104298926","https://openalex.org/W2214409633","https://openalex.org/W2523056285","https://openalex.org/W2560254426","https://openalex.org/W2593768305","https://openalex.org/W2906214917","https://openalex.org/W2998490864","https://openalex.org/W3095303521","https://openalex.org/W3109233127","https://openalex.org/W3206146520","https://openalex.org/W4225281045","https://openalex.org/W4312592225","https://openalex.org/W4372260308","https://openalex.org/W4372341951","https://openalex.org/W4375868847","https://openalex.org/W4375869480","https://openalex.org/W4386158734"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W2361861616","https://openalex.org/W4310988119","https://openalex.org/W4285226279"],"abstract_inverted_index":{"Automatic":[0],"Music":[1],"Transcription":[2],"(AMT)":[3],"is":[4,37],"a":[5,58],"vital":[6],"technology":[7],"in":[8,18,31,107,148],"the":[9,70,92,102,108,139,145,149],"field":[10,150],"of":[11,72,105,129,141,151],"music":[12],"information":[13],"processing.":[14],"Despite":[15],"recent":[16],"enhancements":[17],"performance":[19,117],"due":[20],"to":[21,47,119],"machine":[22],"learning":[23],"techniques,":[24],"current":[25],"methods":[26,90],"typically":[27],"attain":[28],"high":[29],"accuracy":[30],"domains":[32,40],"where":[33,96],"abundant":[34],"annotated":[35],"data":[36,68,110],"available.":[38],"Addressing":[39],"with":[41],"low":[42],"or":[43],"no":[44],"resources":[45],"continues":[46],"be":[48],"an":[49],"unresolved":[50],"challenge.":[51],"To":[52],"tackle":[53],"this":[54,142],"issue,":[55],"we":[56,88],"propose":[57],"transcription":[59],"model":[60],"that":[61],"does":[62],"not":[63,100,124],"require":[64],"any":[65,126],"MIDI-audio":[66],"paired":[67,130],"through":[69],"utilization":[71],"scalable":[73],"synthetic":[74],"audio":[75,106],"for":[76],"pre-training":[77],"and":[78,144],"adversarial":[79],"domain":[80],"confusion":[81],"using":[82],"unannotated":[83],"real":[84,127],"audio.":[85],"In":[86],"experiments,":[87],"evaluate":[89],"under":[91],"real-world":[93],"application":[94],"scenario":[95],"training":[97],"datasets":[98,128],"do":[99],"include":[101],"MIDI":[103],"annotation":[104],"target":[109],"domain.":[111],"Our":[112],"proposed":[113],"method":[114],"achieved":[115],"competitive":[116],"relative":[118],"established":[120],"baseline":[121],"methods,":[122],"despite":[123],"utilizing":[125],"MIDI-audio.":[131],"Additionally,":[132],"ablation":[133],"studies":[134],"have":[135],"provided":[136],"insights":[137],"into":[138],"scalability":[140],"approach":[143],"forthcoming":[146],"challenges":[147],"AMT":[152],"research.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}