{"id":"https://openalex.org/W3008349228","doi":"https://doi.org/10.1109/ssci44817.2019.9002917","title":"Generation of Artificial FO-contours of Emotional Speech with Generative Adversarial Networks","display_name":"Generation of Artificial FO-contours of Emotional Speech with Generative Adversarial Networks","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008349228","doi":"https://doi.org/10.1109/ssci44817.2019.9002917","mag":"3008349228"},"language":"en","primary_location":{"id":"doi:10.1109/ssci44817.2019.9002917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci44817.2019.9002917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5063776512","display_name":"Shumpei Matsuoka","orcid":null},"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":"Shumpei Matsuoka","raw_affiliation_strings":["National institute of advanced science and technology, AIST, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National institute of advanced science and technology, AIST, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040456319","display_name":"Yao Jiang","orcid":"https://orcid.org/0000-0002-5064-0298"},"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":"Yao Jiang","raw_affiliation_strings":["National institute of advanced science and technology, AIST, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National institute of advanced science and technology, AIST, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046057045","display_name":"Akira Sasou","orcid":"https://orcid.org/0000-0003-1700-0325"},"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":"Akira Sasou","raw_affiliation_strings":["National institute of advanced science and technology, AIST, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National institute of advanced science and technology, AIST, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.18832552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1030","last_page":"1034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.998199999332428,"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":0.9973000288009644,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/intension","display_name":"Intension","score":0.8473758101463318},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7868004441261292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6592013835906982},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5173596739768982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49533477425575256},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4939485192298889},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.48890677094459534},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4824264943599701},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.4763363003730774},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.44633397459983826},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34271979331970215},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32145315408706665},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17575526237487793},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12055370211601257},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.10012182593345642}],"concepts":[{"id":"https://openalex.org/C61341680","wikidata":"https://www.wikidata.org/wiki/Q1923256","display_name":"Intension","level":2,"score":0.8473758101463318},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7868004441261292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6592013835906982},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5173596739768982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49533477425575256},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4939485192298889},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.48890677094459534},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4824264943599701},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.4763363003730774},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.44633397459983826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34271979331970215},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32145315408706665},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17575526237487793},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12055370211601257},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.10012182593345642},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci44817.2019.9002917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci44817.2019.9002917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W110071876","https://openalex.org/W167581994","https://openalex.org/W1551113872","https://openalex.org/W2106564373","https://openalex.org/W2123449470","https://openalex.org/W2194775991","https://openalex.org/W2394662942","https://openalex.org/W2801493797","https://openalex.org/W2803193013","https://openalex.org/W2891535489","https://openalex.org/W2922346874","https://openalex.org/W2951523806","https://openalex.org/W2963684088","https://openalex.org/W4295521014","https://openalex.org/W4320013936","https://openalex.org/W6604430519","https://openalex.org/W6606769092","https://openalex.org/W6621378261","https://openalex.org/W6685352114","https://openalex.org/W6712239235","https://openalex.org/W6735913928","https://openalex.org/W6779669310"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Fundamental":[0],"frequency":[1],"(F0)":[2],"contours":[3,38,85,92,115,134],"play":[4],"a":[5,18,29,79],"very":[6,64],"important":[7],"role":[8],"in":[9,20,48,112],"reflecting":[10],"the":[11,67,95,99,104,113,126,131,137,140,147,152],"emotion,":[12],"identity,":[13],"intension,":[14],"and":[15,59,149],"attitude":[16],"of":[17,22,39,56,98,107,110,120,130,139,151],"speaker":[19],"samples":[21],"speech.":[23,41],"In":[24],"this":[25],"paper,":[26],"we":[27],"adopted":[28],"generative":[30,81,121,154],"adversarial":[31],"network":[32],"(GAN)":[33],"to":[34,135],"generate":[35,63,89],"artificial":[36],"F0":[37,84,91,114,133,142],"emotional":[40],"The":[42],"GAN":[43],"faces":[44],"some":[45],"limitations,":[46],"however,":[47],"that":[49,86,93],"it":[50,60],"frequently":[51],"generates":[52],"undesired":[53],"data":[54],"because":[55],"unstable":[57],"training,":[58],"can":[61,87],"repeatedly":[62],"similar":[65],"or":[66],"same":[68],"data,":[69],"which":[70],"is":[71],"known":[72],"as":[73],"mode":[74],"collapse.":[75],"This":[76],"study":[77],"constructed":[78],"GAN-based":[80],"model":[82],"for":[83],"stably":[88],"more-various":[90],"fit":[94],"statistical":[96],"characteristics":[97],"training":[100],"data.":[101],"We":[102,123],"tested":[103],"classification":[105],"rate":[106],"four":[108],"kinds":[109,119],"emotions":[111],"generated":[116,132,141],"from":[117],"five":[118],"models.":[122],"also":[124],"evaluated":[125],"averaged":[127],"local":[128],"density":[129],"represent":[136],"variety":[138],"contours.":[143],"Preliminary":[144],"experiments":[145],"confirmed":[146],"validity":[148],"effectiveness":[150],"proposed":[153],"model.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}