{"id":"https://openalex.org/W3082456152","doi":"https://doi.org/10.1587/transinf.2019edp7297","title":"Joint Adversarial Training of Speech Recognition and Synthesis Models for Many-to-One Voice Conversion Using Phonetic Posteriorgrams","display_name":"Joint Adversarial Training of Speech Recognition and Synthesis Models for Many-to-One Voice Conversion Using Phonetic Posteriorgrams","publication_year":2020,"publication_date":"2020-08-31","ids":{"openalex":"https://openalex.org/W3082456152","doi":"https://doi.org/10.1587/transinf.2019edp7297","mag":"3082456152"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2019edp7297","is_oa":true,"landing_page_url":"http://doi.org/10.1587/transinf.2019edp7297","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/9/E103.D_2019EDP7297/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/9/E103.D_2019EDP7297/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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"]},{"id":"https://openalex.org/I4210156006","display_name":"Deutsche Energy Agency (Germany)","ror":"https://ror.org/05c2nqw49","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210156006"]}],"countries":["DE","JP"],"is_corresponding":true,"raw_author_name":"Yuki SAITO","raw_affiliation_strings":["DeNA Co., Ltd","The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"DeNA Co., Ltd","institution_ids":["https://openalex.org/I4210156006"]},{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050374959","display_name":"Kei Akuzawa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156006","display_name":"Deutsche Energy Agency (Germany)","ror":"https://ror.org/05c2nqw49","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210156006"]},{"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":["DE","JP"],"is_corresponding":false,"raw_author_name":"Kei AKUZAWA","raw_affiliation_strings":["DeNA Co., Ltd","The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"DeNA Co., Ltd","institution_ids":["https://openalex.org/I4210156006"]},{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100925892","display_name":"Kentaro Tachibana","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156006","display_name":"Deutsche Energy Agency (Germany)","ror":"https://ror.org/05c2nqw49","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210156006"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kentaro TACHIBANA","raw_affiliation_strings":["DeNA Co., Ltd"],"affiliations":[{"raw_affiliation_string":"DeNA Co., Ltd","institution_ids":["https://openalex.org/I4210156006"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083394213"],"corresponding_institution_ids":["https://openalex.org/I4210156006","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1021149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E103.D","issue":"9","first_page":"1978","last_page":"1987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9873999953269958,"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/computer-science","display_name":"Computer science","score":0.8766666650772095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8047647476196289},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7615898847579956},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5886695384979248},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5215244889259338},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.48424002528190613},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4464763402938843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39607980847358704},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.365723192691803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8766666650772095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8047647476196289},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7615898847579956},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5886695384979248},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5215244889259338},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.48424002528190613},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4464763402938843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39607980847358704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.365723192691803},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2019edp7297","is_oa":true,"landing_page_url":"http://doi.org/10.1587/transinf.2019edp7297","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/9/E103.D_2019EDP7297/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2019edp7297","is_oa":true,"landing_page_url":"http://doi.org/10.1587/transinf.2019edp7297","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/9/E103.D_2019EDP7297/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4227499671","display_name":null,"funder_award_id":"KAKENHI Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5522210649","display_name":"\u805e\u304d\u624b\u30e2\u30c7\u30eb\u306b\u57fa\u3065\u304f\u80fd\u52d5\u7684\u97f3\u58f0\u5408\u6210\u306b\u95a2\u3059\u308b\u7814\u7a76","funder_award_id":"18J22090","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5786340949","display_name":null,"funder_award_id":"KAKENHI Grant Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3082456152.pdf","grobid_xml":"https://content.openalex.org/works/W3082456152.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W1731081199","https://openalex.org/W1836465849","https://openalex.org/W1965255698","https://openalex.org/W1995562189","https://openalex.org/W2003235278","https://openalex.org/W2007023536","https://openalex.org/W2095705004","https://openalex.org/W2100495367","https://openalex.org/W2102003408","https://openalex.org/W2109553965","https://openalex.org/W2120605154","https://openalex.org/W2125389028","https://openalex.org/W2126143605","https://openalex.org/W2129142580","https://openalex.org/W2142300631","https://openalex.org/W2146502635","https://openalex.org/W2156142001","https://openalex.org/W2293635543","https://openalex.org/W2294013337","https://openalex.org/W2471520273","https://openalex.org/W2475998840","https://openalex.org/W2518172956","https://openalex.org/W2519648275","https://openalex.org/W2532494225","https://openalex.org/W2747744257","https://openalex.org/W2787685498","https://openalex.org/W2801581493","https://openalex.org/W2804998325","https://openalex.org/W2897353073","https://openalex.org/W2899877258","https://openalex.org/W2902070858","https://openalex.org/W2937579788","https://openalex.org/W2938583109","https://openalex.org/W2938836228","https://openalex.org/W2962684181","https://openalex.org/W2962699523","https://openalex.org/W2962793481","https://openalex.org/W2963035245","https://openalex.org/W2963539064","https://openalex.org/W2963767194","https://openalex.org/W2963808252","https://openalex.org/W2963830550","https://openalex.org/W2963971656","https://openalex.org/W2972399707","https://openalex.org/W2972667718","https://openalex.org/W2973108288","https://openalex.org/W3099078140"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W2946768379","https://openalex.org/W2551249631"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,30,74,89],"method":[4,24,72,129],"for":[5,25,81,100,121],"many-to-one":[6,26],"voice":[7],"conversion":[8],"using":[9],"phonetic":[10],"posteriorgrams":[11],"(PPGs)":[12],"based":[13],"on":[14],"an":[15,60],"adversarial":[16,91],"training":[17,76,95],"of":[18,63,77,96],"deep":[19],"neural":[20],"networks":[21],"(DNNs).A":[22],"conventional":[23,106,138],"VC":[27,139],"can":[28],"learn":[29],"mapping":[31],"function":[32],"from":[33],"input":[34],"acoustic":[35,39,65],"features":[36,40,66],"to":[37],"target":[38],"through":[41],"separately":[42],"trained":[43],"DNN-based":[44],"speech":[45,70,134],"recognition":[46,79,112],"and":[47,58,113],"synthesis":[48,98,114],"models.However,":[49],"1)":[50],"the":[51,68,78,83,94,97,102,105,111,127,132],"differences":[52],"among":[53],"speakers":[54],"observed":[55],"in":[56],"PPGs":[57],"2)":[59],"over-smoothing":[61],"effect":[62],"generated":[64],"degrade":[67],"converted":[69,133],"quality.Our":[71],"performs":[73],"domain-adversarial":[75],"model":[80,99],"reducing":[82],"PPG":[84],"differences.In":[85],"addition,":[86],"it":[87],"incorporates":[88],"generative":[90],"network":[92],"into":[93],"alleviating":[101],"oversmoothing":[103],"effect.Unlike":[104],"method,":[107],"ours":[108],"jointly":[109],"trains":[110],"models":[115],"so":[116],"that":[117,126],"they":[118],"are":[119],"optimized":[120],"many-toone":[122],"VC.Experimental":[123],"evaluation":[124],"demonstrates":[125],"proposed":[128],"significantly":[130],"improves":[131],"quality":[135],"compared":[136],"with":[137],"methods.":[140]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}