{"id":"https://openalex.org/W3015687355","doi":"https://doi.org/10.1109/icassp40776.2020.9053844","title":"Humangan: Generative Adversarial Network With Human-Based Discriminator And Its Evaluation In Speech Perception Modeling","display_name":"Humangan: Generative Adversarial Network With Human-Based Discriminator And Its Evaluation In Speech Perception Modeling","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015687355","doi":"https://doi.org/10.1109/icassp40776.2020.9053844","mag":"3015687355"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053844","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/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":true,"raw_author_name":"Kazuki Fujii","raw_affiliation_strings":["National Institute of Technology, Tokuyama College, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Technology, Tokuyama College, 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":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"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":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"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":["Faculty of Engineering, University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, 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":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"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":5,"corresponding_author_ids":["https://openalex.org/A5028262563"],"corresponding_institution_ids":["https://openalex.org/I4210142609"],"apc_list":null,"apc_paid":null,"fwci":0.7577,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69677419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"j102 d","issue":null,"first_page":"6239","last_page":"6243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9988999962806702,"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/discriminator","display_name":"Discriminator","score":0.9800166487693787},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7346228957176208},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7109090089797974},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6916480660438538},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5777973532676697},{"id":"https://openalex.org/keywords/human-voice","display_name":"Human voice","score":0.5654848217964172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.504562497138977},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.49025920033454895},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09196346998214722}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9800166487693787},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7346228957176208},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7109090089797974},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6916480660438538},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5777973532676697},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.5654848217964172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.504562497138977},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.49025920033454895},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09196346998214722},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053844","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053844","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":[{"display_name":"Reduced inequalities","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1502984613","https://openalex.org/W2051368408","https://openalex.org/W2099471712","https://openalex.org/W2125389028","https://openalex.org/W2170989440","https://openalex.org/W2471520273","https://openalex.org/W2519648275","https://openalex.org/W2577946330","https://openalex.org/W2593021375","https://openalex.org/W2808698466","https://openalex.org/W2889498027","https://openalex.org/W2939924693","https://openalex.org/W2951882630","https://openalex.org/W2963062382","https://openalex.org/W2963143316","https://openalex.org/W2963971656","https://openalex.org/W2964268978","https://openalex.org/W4320013936","https://openalex.org/W6678815747","https://openalex.org/W6683074461","https://openalex.org/W6732248266","https://openalex.org/W6734269522","https://openalex.org/W6750404860","https://openalex.org/W6754343397"],"related_works":["https://openalex.org/W4293320219","https://openalex.org/W2953246223","https://openalex.org/W3110074278","https://openalex.org/W4283584549","https://openalex.org/W2554314924","https://openalex.org/W4288256692","https://openalex.org/W2998859928","https://openalex.org/W3156863413","https://openalex.org/W4381885966","https://openalex.org/W2969399009"],"abstract_inverted_index":{"We":[0,125],"propose":[1],"the":[2,28,37,42,49,88,93],"HumanGAN,":[3],"a":[4,13,19,23,45,65,73,80,98,108,119,139,146],"generative":[5],"adversarial":[6],"network":[7],"(GAN)":[8],"incorporating":[9],"human":[10,59,70,105],"perception":[11,106],"as":[12,69,107],"discriminator.":[14,110],"A":[15],"basic":[16,38,89],"GAN":[17,39],"trains":[18],"generator":[20,100,115],"to":[21],"represent":[22,41,138],"real-data":[24,46,81,147],"distribution":[25,75,141],"by":[26,87,103,117,123],"fooling":[27],"discriminator":[29],"that":[30,135,142],"distinguishes":[31],"real":[32],"and":[33,83,121,133],"generated":[34],"data.":[35],"Therefore,":[36],"cannot":[40,84],"outside":[43],"of":[44,51],"distribution.":[47,148],"In":[48],"case":[50],"speech":[52,130],"perception,":[53],"humans":[54],"can":[55,137],"recognize":[56],"not":[57],"only":[58],"voices":[60,68],"but":[61],"also":[62],"processed":[63],"(i.e.,":[64],"non-existent":[66],"human)":[67],"voice.":[71],"Such":[72],"human-acceptable":[74,94,140],"is":[76,143],"typically":[77],"wider":[78,144],"than":[79,145],"one":[82],"be":[85],"modeled":[86],"GAN.":[90],"To":[91],"model":[92],"distribution,":[95],"we":[96],"formulate":[97],"backpropagation-based":[99],"training":[101,112,116],"algorithm":[102],"regarding":[104],"black-boxed":[109],"The":[111],"efficiently":[113],"iterates":[114],"using":[118],"computer":[120],"discrimination":[122],"human.":[124],"evaluate":[126],"our":[127],"HumanGAN":[128],"in":[129],"naturalness":[131],"modeling":[132],"demonstrate":[134],"it":[136]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
