{"id":"https://openalex.org/W3162052267","doi":"https://doi.org/10.1109/icassp39728.2021.9413363","title":"Humanacgan: Conditional Generative Adversarial Network with Human-Based Auxiliary Classifier and its Evaluation in Phoneme Perception","display_name":"Humanacgan: Conditional Generative Adversarial Network with Human-Based Auxiliary Classifier and its Evaluation in Phoneme Perception","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162052267","doi":"https://doi.org/10.1109/icassp39728.2021.9413363","mag":"3162052267"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5062412090","display_name":"Yota Ueda","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yota Ueda","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028262563","display_name":"Kazuki Fujii","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142609","display_name":"National Institute of Technology, Tokuyama College","ror":"https://ror.org/046jx2h22","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120810","https://openalex.org/I4210142609"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuki Fujii","raw_affiliation_strings":["National Institute of Technology,Tokuyama College,Japan","Tokuyama College, National Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Technology,Tokuyama College,Japan","institution_ids":["https://openalex.org/I4210142609"]},{"raw_affiliation_string":"Tokuyama College, National Institute of Technology, Japan","institution_ids":["https://openalex.org/I4210142609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010710732","display_name":"Yukino Baba","orcid":"https://orcid.org/0000-0001-5310-9841"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukino Baba","raw_affiliation_strings":["University of Tsukuba,Faculty of Engineering, Information and Systems,Japan","Faculty of Engineering, Information and Systems, University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba,Faculty of Engineering, Information and Systems,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"Faculty of Engineering, Information and Systems, University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo,Graduate School of Information Science and Technology,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Graduate School of Information Science and Technology,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5062412090"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.1524,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41372549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"6468","last_page":"6472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/discriminator","display_name":"Discriminator","score":0.9657562375068665},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.74294114112854},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7336576581001282},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7033208608627319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6189871430397034},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5479167103767395},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.527698278427124},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5002894401550293},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4579628109931946},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.41466712951660156},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4119924306869507},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.411773681640625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36225175857543945}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9657562375068665},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.74294114112854},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7336576581001282},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7033208608627319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6189871430397034},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5479167103767395},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.527698278427124},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5002894401550293},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4579628109931946},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41466712951660156},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4119924306869507},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.411773681640625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36225175857543945},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1502984613","https://openalex.org/W1583912456","https://openalex.org/W1959608418","https://openalex.org/W2099471712","https://openalex.org/W2115040572","https://openalex.org/W2125389028","https://openalex.org/W2156142001","https://openalex.org/W2471520273","https://openalex.org/W2519648275","https://openalex.org/W2548275288","https://openalex.org/W2577946330","https://openalex.org/W2787535773","https://openalex.org/W2940405045","https://openalex.org/W2951882630","https://openalex.org/W2963062382","https://openalex.org/W2963971656","https://openalex.org/W2964020555","https://openalex.org/W3015687355","https://openalex.org/W3048790906","https://openalex.org/W4320013936","https://openalex.org/W6635084905","https://openalex.org/W6640963894","https://openalex.org/W6678815747","https://openalex.org/W6729482032","https://openalex.org/W6732248266","https://openalex.org/W6748161763","https://openalex.org/W6750404860"],"related_works":["https://openalex.org/W2953246223","https://openalex.org/W4293320219","https://openalex.org/W3110074278","https://openalex.org/W4283584549","https://openalex.org/W2618858825","https://openalex.org/W2554314924","https://openalex.org/W2998859928","https://openalex.org/W3151498616","https://openalex.org/W4381885966","https://openalex.org/W4288256692"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,19,23,31,69,94,109,119],"conditional":[3,87,103,111,177],"generative":[4],"adversarial":[5],"network":[6,15],"(GAN)":[7],"incorporating":[8],"humans\u2019":[9,73,160],"perceptual":[10,74,148,161],"evaluations.":[11,162],"A":[12,54,63],"deep":[13],"neural":[14],"(DNN)-based":[16],"generator":[17,65,112,127],"of":[18,37,46,77,97],"GAN":[20],"can":[21,28,152,173],"represent":[22,30,86],"real-data":[24],"distribution":[25],"accurately":[26],"but":[27,121],"never":[29],"human-acceptable":[32,61,104],"distribution,":[33],"which":[34,40],"are":[35,50],"ranges":[36],"data":[38,49],"in":[39,166],"humans":[41,115],"accept":[42],"the":[43,48,60,78,83,92,98,132,137,141,146,156],"naturalness":[44,139],"regardless":[45],"whether":[47],"real":[51],"or":[52],"not.":[53],"Human-GAN":[55],"was":[56],"proposed":[57],"to":[58,100],"model":[59],"distribution.":[62],"DNN-based":[64,80,110],"is":[66,128],"trained":[67,129],"using":[68,155],"human-based":[70,133,142],"discriminator,":[71],"i.e.,":[72],"evaluations,":[75],"instead":[76],"GAN\u2019s":[79],"discriminator.":[81],"However,":[82],"HumanGAN":[84],"cannot":[85],"distributions.":[88,105],"This":[89],"paper":[90],"proposes":[91],"HumanACGAN,":[93],"theoretical":[95],"extension":[96],"HumanGAN,":[99],"deal":[101],"with":[102],"Our":[106,163],"HumanACGAN":[107,172],"trains":[108],"by":[113,130],"regarding":[114],"as":[116],"not":[117],"only":[118],"discriminator":[120,134],"also":[122],"an":[123],"auxiliary":[124],"classifier.":[125],"The":[126,150],"deceiving":[131],"that":[135,144,170],"scores":[136,145],"unconditioned":[138],"and":[140],"classifier":[143],"class-conditioned":[147],"acceptability.":[149],"training":[151],"be":[153],"executed":[154],"backpropagation":[157],"algorithm":[158],"involving":[159],"experimental":[164],"results":[165],"phoneme":[167],"perception":[168],"demonstrate":[169],"our":[171],"successfully":[174],"train":[175],"this":[176],"generator.":[178]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}