{"id":"https://openalex.org/W2939957001","doi":"https://doi.org/10.1109/icassp.2019.8683024","title":"Automatic Singing Transcription Based on Encoder-decoder Recurrent Neural Networks with a Weakly-supervised Attention Mechanism","display_name":"Automatic Singing Transcription Based on Encoder-decoder Recurrent Neural Networks with a Weakly-supervised Attention Mechanism","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939957001","doi":"https://doi.org/10.1109/icassp.2019.8683024","mag":"2939957001"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5025832278","display_name":"Ryo Nishikimi","orcid":"https://orcid.org/0000-0002-3638-6115"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Nishikimi","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043140898","display_name":"Eita Nakamura","orcid":"https://orcid.org/0000-0003-4097-6027"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eita Nakamura","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003098968","display_name":"Satoru Fukayama","orcid":"https://orcid.org/0000-0001-6506-2796"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoru Fukayama","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"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":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"165"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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/singing","display_name":"Singing","score":0.877211332321167},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7868428230285645},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.697677493095398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6830927729606628},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6163694858551025},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.5303769111633301},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.46679314970970154},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.463589608669281},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4333137273788452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42491504549980164},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35446077585220337},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.23099616169929504},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10373637080192566}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.877211332321167},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868428230285645},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.697677493095398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6830927729606628},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6163694858551025},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.5303769111633301},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.46679314970970154},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.463589608669281},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4333137273788452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42491504549980164},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35446077585220337},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.23099616169929504},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10373637080192566},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/icassp.2019.8683024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W774541572","https://openalex.org/W854541894","https://openalex.org/W1519655822","https://openalex.org/W1522301498","https://openalex.org/W1526336542","https://openalex.org/W1677182931","https://openalex.org/W1902237438","https://openalex.org/W1964208564","https://openalex.org/W1976069042","https://openalex.org/W2023800933","https://openalex.org/W2024514957","https://openalex.org/W2029337446","https://openalex.org/W2100989275","https://openalex.org/W2118774185","https://openalex.org/W2133564696","https://openalex.org/W2164098335","https://openalex.org/W2166209411","https://openalex.org/W2169784142","https://openalex.org/W2206275834","https://openalex.org/W2327501763","https://openalex.org/W2400676457","https://openalex.org/W2635912764","https://openalex.org/W2749514303","https://openalex.org/W2756044476","https://openalex.org/W2771763364","https://openalex.org/W2778460379","https://openalex.org/W2885029858","https://openalex.org/W2899771611","https://openalex.org/W2921533722","https://openalex.org/W2963920996","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W6622488751","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6631117800","https://openalex.org/W6631190155","https://openalex.org/W6679434410","https://openalex.org/W6713148187","https://openalex.org/W6744199053","https://openalex.org/W6746486700","https://openalex.org/W6753762981","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W4313563496","https://openalex.org/W1521429553","https://openalex.org/W2182291269","https://openalex.org/W1970915741","https://openalex.org/W2229159429","https://openalex.org/W2036853899","https://openalex.org/W127992326"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"neural":[3],"singing":[4,19,33,85,190],"transcription":[5,34],"that":[6,111,183],"estimates":[7],"a":[8,147,171],"sequence":[9],"of":[10,18,48,84,128,155,167],"musical":[11,43,91],"notes":[12,92,157],"directly":[13],"from":[14,121],"the":[15,56,62,152,165,168],"audio":[16],"signal":[17],"voice":[20,191],"in":[21,138,192],"an":[22,104,108,115],"end-to-end":[23],"manner":[24],"without":[25],"time-aligned":[26,96,156],"training":[27,123],"data.":[28,124],"A":[29],"conventional":[30],"approach":[31],"to":[32,36,61,80,90,132,140],"is":[35,52,76,131],"perform":[37],"vocal":[38],"F0":[39,57],"estimation":[40,58,64],"followed":[41],"by":[42],"note":[44,63],"estimation.":[45],"The":[46,125],"performance":[47],"this":[49],"approach,":[50],"however,":[51],"severely":[53],"limited":[54],"because":[55],"errors":[59],"propagate":[60],"step":[65],"and":[66,78,118],"rich":[67],"acoustic":[68],"information":[69],"cannot":[70],"be":[71,176],"used.":[72],"In":[73],"addition,":[74],"it":[75],"difficult":[77],"time-consuming":[79],"split":[81],"continuous":[82],"signals":[83],"voices":[86],"into":[87],"segments":[88],"corresponding":[89],"for":[93,151,158,188],"making":[94],"precise":[95],"transcriptions.":[97],"To":[98],"solve":[99],"these":[100],"problems,":[101],"we":[102],"use":[103],"encoder-decoder":[105],"model":[106],"with":[107],"attention":[109,153],"mechanism":[110],"can":[112,175],"automatically":[113],"learn":[114],"input-output":[116,173],"alignment":[117,160,174],"mapping,":[119],"even":[120],"non-aligned":[122],"main":[126],"challenge":[127],"our":[129,184],"study":[130],"estimate":[133],"temporal":[134],"categories":[135,142],"(note":[136],"values)":[137],"addition":[139],"instantaneous":[141],"(pitches).":[143],"We":[144,181],"thus":[145],"propose":[146],"novel":[148],"loss":[149,169],"function":[150],"weights":[154],"semi-supervised":[159],"training.":[161],"By":[162],"gradually":[163],"reducing":[164],"weight":[166],"function,":[170],"better":[172],"learned":[177],"much":[178],"more":[179],"quickly.":[180],"showed":[182],"method":[185],"performed":[186],"well":[187],"isolated":[189],"popular":[193],"music.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}