{"id":"https://openalex.org/W3095798115","doi":"https://doi.org/10.1109/taslp.2020.3035001","title":"Semi-Supervised Neural Chord Estimation Based on a Variational Autoencoder With Latent Chord Labels and Features","display_name":"Semi-Supervised Neural Chord Estimation Based on a Variational Autoencoder With Latent Chord Labels and Features","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3095798115","doi":"https://doi.org/10.1109/taslp.2020.3035001","mag":"3095798115"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3035001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3035001","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101463862","display_name":"Yiming Wu","orcid":"https://orcid.org/0000-0003-1388-7192"},"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yiming Wu","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan","Graduate School of Informatics Kyoto University Kyoto Japan"],"raw_orcid":"https://orcid.org/0000-0003-1388-7192","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics Kyoto University Kyoto Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026032571","display_name":"Tristan Carsault","orcid":null},"institutions":[{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Tristan Carsault","raw_affiliation_strings":["Repr\u00e9sentations Musicales, IRCAM, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Repr\u00e9sentations Musicales, IRCAM, Paris, France","institution_ids":["https://openalex.org/I35345632"]}]},{"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eita Nakamura","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan","Hakubi Center for Advanced Research, Kyoto University, Kyoto, Japan","Graduate School of Informatics Kyoto University Kyoto Japan"],"raw_orcid":"https://orcid.org/0000-0003-4097-6027","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Hakubi Center for Advanced Research, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics Kyoto University Kyoto Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"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"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan","Graduate School of Informatics Kyoto University Kyoto Japan"],"raw_orcid":"https://orcid.org/0000-0001-8387-8609","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics Kyoto University Kyoto Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101463862"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I39012071"],"apc_list":null,"apc_paid":null,"fwci":0.4558,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.62553886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"2956","last_page":"2966"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9973000288009644,"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":0.9939000010490417,"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/discriminative-model","display_name":"Discriminative model","score":0.7529468536376953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6827505826950073},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6763193607330322},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6064816117286682},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5816431045532227},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5375245809555054},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.5331140756607056},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.520186185836792},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5070633888244629},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4799385666847229},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45802199840545654},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4519375264644623},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.4361993670463562},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36619919538497925},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3270721435546875},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10032385587692261}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7529468536376953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6827505826950073},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6763193607330322},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6064816117286682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5816431045532227},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5375245809555054},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.5331140756607056},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.520186185836792},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5070633888244629},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4799385666847229},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45802199840545654},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4519375264644623},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4361993670463562},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36619919538497925},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3270721435546875},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10032385587692261},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2020.3035001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3035001","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[{"id":"https://openalex.org/G3489341541","display_name":null,"funder_award_id":"19H04137","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3662680752","display_name":null,"funder_award_id":"16H01744","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4515010323","display_name":null,"funder_award_id":"19K20340","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338113","display_name":"Accelerated Innovation Research Initiative Turning Top Science and Ideas into High-Impact Values","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W137288188","https://openalex.org/W216397362","https://openalex.org/W296482991","https://openalex.org/W774541572","https://openalex.org/W1494080199","https://openalex.org/W1503560067","https://openalex.org/W1519655822","https://openalex.org/W1522301498","https://openalex.org/W1880726444","https://openalex.org/W1959608418","https://openalex.org/W1982446897","https://openalex.org/W2005708641","https://openalex.org/W2051672531","https://openalex.org/W2073228908","https://openalex.org/W2108501770","https://openalex.org/W2111007352","https://openalex.org/W2125838338","https://openalex.org/W2165320163","https://openalex.org/W2166435644","https://openalex.org/W2294150958","https://openalex.org/W2296557957","https://openalex.org/W2395935897","https://openalex.org/W2398360960","https://openalex.org/W2398597216","https://openalex.org/W2403726878","https://openalex.org/W2407685581","https://openalex.org/W2547875792","https://openalex.org/W2552400013","https://openalex.org/W2771265026","https://openalex.org/W2774265474","https://openalex.org/W2886597424","https://openalex.org/W2900365452","https://openalex.org/W2902983770","https://openalex.org/W2946729882","https://openalex.org/W2949408457","https://openalex.org/W2949416428","https://openalex.org/W2963043971","https://openalex.org/W2963403868","https://openalex.org/W2963739817","https://openalex.org/W2963794160","https://openalex.org/W2963891243","https://openalex.org/W2964121744","https://openalex.org/W2983598429","https://openalex.org/W2990800437","https://openalex.org/W2991377373","https://openalex.org/W2991512180","https://openalex.org/W3099271704","https://openalex.org/W4297824908","https://openalex.org/W4385245566","https://openalex.org/W6605537023","https://openalex.org/W6608682707","https://openalex.org/W6610543779","https://openalex.org/W6622488751","https://openalex.org/W6629482062","https://openalex.org/W6630180946","https://openalex.org/W6631117800","https://openalex.org/W6631190155","https://openalex.org/W6639340343","https://openalex.org/W6640963894","https://openalex.org/W6675944832","https://openalex.org/W6676368125","https://openalex.org/W6697136871","https://openalex.org/W6697297547","https://openalex.org/W6712324461","https://openalex.org/W6712497386","https://openalex.org/W6713578759","https://openalex.org/W6714030504","https://openalex.org/W6729448088","https://openalex.org/W6739901393","https://openalex.org/W6746411809","https://openalex.org/W6746815159","https://openalex.org/W6751254666","https://openalex.org/W6753775506","https://openalex.org/W6756673966","https://openalex.org/W6765720210","https://openalex.org/W6770388877","https://openalex.org/W6770607572","https://openalex.org/W6771230977","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W3003379904","https://openalex.org/W2771099609","https://openalex.org/W1503442776","https://openalex.org/W2963736354","https://openalex.org/W2964031641","https://openalex.org/W2740593609","https://openalex.org/W2952671313","https://openalex.org/W2962974924","https://openalex.org/W2128416415","https://openalex.org/W2399306074"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,35,43,74,91,118,124,159,168],"statistically-principled":[4],"semi-supervised":[5,169,208],"method":[6],"of":[7,17,21,24,83,100,138,178,187,194,200],"automatic":[8],"chord":[9,25,40,59,188],"estimation":[10],"(ACE)":[11],"that":[12,95,175],"can":[13,163,214],"make":[14],"effective":[15],"use":[16],"music":[18,50],"signals":[19],"regardless":[20],"the":[22,81,97,135,139,176,179,184,191,198,204,217],"availability":[23],"annotations.":[26],"The":[27,171,207],"typical":[28],"approach":[29,79],"to":[30,33,116],"ACE":[31,201],"is":[32],"train":[34],"deep":[36,92,149],"classification":[37,150,180],"model":[38,94,120,181,193],"(neural":[39],"estimator)":[41],"in":[42,80,167],"supervised":[44,205],"manner":[45],"by":[46,147],"using":[47,148,210],"only":[48],"annotated":[49],"signals.":[51],"In":[52,70],"this":[53],"discriminative":[54,78],"approach,":[55],"prior":[56,186],"knowledge":[57],"about":[58],"label":[60],"sequences":[61],"(model":[62],"output)":[63],"has":[64],"scarcely":[65],"been":[66],"taken":[67],"into":[68],"account.":[69],"contrast,":[71],"we":[72,89],"propose":[73],"unified":[75],"generative":[76,93,98,192],"and":[77,108,123,142,151,162,190],"framework":[82],"amortized":[84],"variational":[85,160],"inference.":[86],"More":[87],"specifically,":[88],"formulate":[90],"represents":[96],"process":[99],"chroma":[101,130,195],"vectors":[102,131,196],"(observed":[103],"variables)":[104],"from":[105],"discrete":[106],"labels":[107,141,189],"continuous":[109],"features":[110,143],"(latent":[111],"variables),":[112],"which":[113],"are":[114,144],"assumed":[115],"follow":[117],"Markov":[119,185],"favoring":[121],"self-transitions":[122],"standard":[125],"Gaussian":[126],"distribution,":[127],"respectively.":[128,154],"Given":[129],"as":[132],"observed":[133],"data,":[134],"posterior":[136],"distributions":[137],"latent":[140],"computed":[145],"approximately":[146],"recognition":[152],"models,":[153],"These":[155],"three":[156],"models":[157],"form":[158],"autoencoder":[161],"be":[164],"trained":[165],"jointly":[166],"manner.":[170],"experimental":[172],"results":[173],"show":[174],"regularization":[177],"based":[182],"on":[183],"improved":[197],"performance":[199],"even":[202],"under":[203],"condition.":[206],"learning":[209],"additional":[211],"non-annotated":[212],"data":[213],"further":[215],"improve":[216],"performance.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-10T08:33:47.465468","created_date":"2025-10-10T00:00:00"}