{"id":"https://openalex.org/W3015247127","doi":"https://doi.org/10.1109/icassp40776.2020.9052987","title":"Improving Music Transcription by Pre-Stacking A U-Net","display_name":"Improving Music Transcription by Pre-Stacking A U-Net","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015247127","doi":"https://doi.org/10.1109/icassp40776.2020.9052987","mag":"3015247127"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9052987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5048007228","display_name":"Fabrizio Pedersoli","orcid":null},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Fabrizio Pedersoli","raw_affiliation_strings":["Department of Computer Science, University of Victoria"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010445045","display_name":"George Tzanetakis","orcid":"https://orcid.org/0000-0002-6844-7912"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"George Tzanetakis","raw_affiliation_strings":["Department of Computer Science, University of Victoria"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049893251","display_name":"Kwang Moo Yi","orcid":"https://orcid.org/0000-0001-9036-3822"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kwang Moo Yi","raw_affiliation_strings":["Department of Computer Science, University of Victoria"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Victoria","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048007228"],"corresponding_institution_ids":["https://openalex.org/I212119943"],"apc_list":null,"apc_paid":null,"fwci":1.6669,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.84147465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"506","last_page":"510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9961000084877014,"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":0.9908999800682068,"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/computer-science","display_name":"Computer science","score":0.7328540086746216},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7295300960540771},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5895054340362549},{"id":"https://openalex.org/keywords/transcription-factor","display_name":"Transcription factor","score":0.4388121962547302},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.4365655183792114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38606229424476624},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.24958795309066772},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14759597182273865},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08534607291221619},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.07100197672843933}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7328540086746216},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7295300960540771},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5895054340362549},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.4388121962547302},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.4365655183792114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38606229424476624},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.24958795309066772},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14759597182273865},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08534607291221619},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.07100197672843933},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9052987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":38,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1797486849","https://openalex.org/W1901129140","https://openalex.org/W2023800933","https://openalex.org/W2104112890","https://openalex.org/W2104298926","https://openalex.org/W2104299881","https://openalex.org/W2105343238","https://openalex.org/W2133240958","https://openalex.org/W2135151673","https://openalex.org/W2139122061","https://openalex.org/W2144414181","https://openalex.org/W2166368937","https://openalex.org/W2194775991","https://openalex.org/W2198584637","https://openalex.org/W2295460171","https://openalex.org/W2559688696","https://openalex.org/W2773294482","https://openalex.org/W2774707525","https://openalex.org/W2963045359","https://openalex.org/W2963452667","https://openalex.org/W2963551352","https://openalex.org/W2964121744","https://openalex.org/W4293775315","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638303826","https://openalex.org/W6639824700","https://openalex.org/W6675456757","https://openalex.org/W6679714990","https://openalex.org/W6697000175","https://openalex.org/W6730401039","https://openalex.org/W6745851314","https://openalex.org/W6746836464","https://openalex.org/W6746914816","https://openalex.org/W6751512325"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W2590798552","https://openalex.org/W2811106690","https://openalex.org/W4239306820","https://openalex.org/W2947043951","https://openalex.org/W2318112981","https://openalex.org/W4312417841","https://openalex.org/W4210874298"],"abstract_inverted_index":{"We":[0,78,105],"propose":[1],"to":[2,53,139],"pre-stack":[3],"a":[4,7,25,35,40,89],"U-Net":[5,82],"as":[6,34],"way":[8],"of":[9,16,123],"improving":[10],"the":[11,54,61,66,74,85,100,112,116,121,140,148,168],"polyphonic":[12],"music":[13,156],"transcription":[14,41,76,124,157,160,171],"performance":[15,172],"various":[17],"baseline":[18,141],"Convolutional":[19],"Neural":[20],"Networks":[21],"(CNNS).":[22],"The":[23],"U-Net,":[24],"network":[26,37,83],"architecture":[27,150],"based":[28],"on":[29],"skip-connections":[30],"between":[31],"layers":[32,138],"acts":[33],"transformation":[36,55],"followed":[38],"by":[39,131],"network.":[42,77],"Notably,":[43],"we":[44,144,151],"do":[45],"not":[46],"introduce":[47],"any":[48],"additional":[49],"loss":[50,68],"terms":[51],"specific":[52],"network,":[56],"but":[57],"instead,":[58],"jointly":[59],"train":[60],"entire":[62],"combined":[63],"model":[64],"with":[65,108],"original":[67,169],"function":[69],"that":[70,80,91,115,146],"was":[71],"designed":[72],"for":[73,95],"back-end":[75],"argue":[79],"this":[81],"transforms":[84],"input":[86],"signal":[87],"into":[88],"representation":[90],"is":[92,173],"more":[93,134,137],"effective":[94],"transcription,":[96],"and":[97,158],"thus":[98],"enables":[99],"observed":[101],"improvements":[102],"in":[103,161],"accuracy.":[104],"empirically":[106],"confirm":[107],"several":[109],"experiments":[110],"using":[111,147],"MusicNet":[113],"dataset,":[114],"proposed":[117,149],"configuration":[118],"consistently":[119],"improves":[120],"accuracy":[122],"networks.":[125],"This":[126],"enhancement":[127],"cannot":[128],"be":[129],"achieved":[130],"simply":[132],"introducing":[133],"neurons":[135],"or":[136],"CNNs.":[142],"Moreover,":[143],"show":[145],"can":[152],"go":[153],"beyond":[154],"general":[155,170],"perform":[159],"an":[162],"instrument-specific":[163],"fashion.":[164],"By":[165],"doing":[166],"so,":[167],"also":[174],"increased.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}