{"id":"https://openalex.org/W2532494225","doi":"https://doi.org/10.1109/apsipa.2016.7820786","title":"Voice conversion from non-parallel corpora using variational auto-encoder","display_name":"Voice conversion from non-parallel corpora using variational auto-encoder","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2532494225","doi":"https://doi.org/10.1109/apsipa.2016.7820786","mag":"2532494225"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2016.7820786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2016.7820786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5028115568","display_name":"Chin-Cheng Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chin-Cheng Hsu","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101061014","display_name":"Hsin-Te Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Te Hwang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.7832,"has_fulltext":false,"cited_by_count":296,"citation_normalized_percentile":{"value":0.99175839,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"2016","issue":null,"first_page":"1","last_page":"6"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9969000220298767,"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/T12031","display_name":"Speech and dialogue systems","score":0.9919999837875366,"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/computer-science","display_name":"Computer science","score":0.8806742429733276},{"id":"https://openalex.org/keywords/unavailability","display_name":"Unavailability","score":0.7409051060676575},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6554152965545654},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.6258214116096497},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6194078922271729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5407417416572571},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5135922431945801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5122917890548706},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.47088178992271423},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4164672791957855},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.21938112378120422},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1224062442779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8806742429733276},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.7409051060676575},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6554152965545654},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.6258214116096497},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6194078922271729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5407417416572571},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5135922431945801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5122917890548706},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.47088178992271423},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4164672791957855},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.21938112378120422},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1224062442779541},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipa.2016.7820786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2016.7820786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"},{"id":"mag:2750516925","is_oa":false,"landing_page_url":"http://jglobal.jst.go.jp/en/public/20090422/201702297657446665","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7099999785423279,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1517202054","https://openalex.org/W1520370180","https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1959608418","https://openalex.org/W1977362459","https://openalex.org/W2019849101","https://openalex.org/W2032130465","https://openalex.org/W2049686551","https://openalex.org/W2067175291","https://openalex.org/W2108501770","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2156477760","https://openalex.org/W2157412983","https://openalex.org/W2161476805","https://openalex.org/W2169579015","https://openalex.org/W2290463584","https://openalex.org/W2290946177","https://openalex.org/W2294351487","https://openalex.org/W2407281753","https://openalex.org/W2473388484","https://openalex.org/W2512087624","https://openalex.org/W2949416428","https://openalex.org/W2964121744","https://openalex.org/W6631184489","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6640963894","https://openalex.org/W6675944832","https://openalex.org/W6696767757"],"related_works":["https://openalex.org/W4237235066","https://openalex.org/W207884067","https://openalex.org/W3127016596","https://openalex.org/W2026539069","https://openalex.org/W2365973415","https://openalex.org/W3146085540","https://openalex.org/W1482423459","https://openalex.org/W2996457675","https://openalex.org/W2129918226","https://openalex.org/W2970195534"],"abstract_inverted_index":{"We":[0,63,115],"propose":[1,64],"a":[2,34,90,111],"flexible":[3],"framework":[4,67,80],"for":[5,27,32],"spectral":[6,112],"conversion":[7,29,113],"(SC)":[8],"that":[9,84,92,132],"facilitates":[10],"training":[11],"with":[12,37],"unaligned":[13],"corpora.":[14,62,78,137],"Many":[15],"SC":[16,53,66,130],"frameworks":[17],"require":[18],"parallel":[19,61,104],"corpora,":[20],"phonetic":[21,87,107],"alignments,":[22],"or":[23,31,57,106],"explicit":[24],"frame-wise":[25],"correspondence":[26],"learning":[28],"functions":[30],"synthesizing":[33],"target":[35],"spectrum":[36],"the":[38,47,96,101],"aid":[39],"of":[40,49,52,60,103],"alignments.":[41],"However,":[42],"these":[43],"requirements":[44],"gravely":[45],"limit":[46],"scope":[48],"practical":[50],"applications":[51],"due":[54],"to":[55,75,94,109,121,129,135],"scarcity":[56],"even":[58],"unavailability":[59],"an":[65,82],"based":[68],"on":[69],"variational":[70],"auto-encoder":[71],"which":[72],"enables":[73],"us":[74],"exploit":[76],"non-parallel":[77],"The":[79],"comprises":[81],"encoder":[83],"learns":[85,93],"speaker-independent":[86],"representations":[88],"and":[89,118,126],"decoder":[91],"reconstruct":[95],"designated":[97],"speaker.":[98],"It":[99],"removes":[100],"requirement":[102],"corpora":[105],"alignments":[108],"train":[110],"system.":[114],"report":[116],"objective":[117],"subjective":[119],"evaluations":[120],"validate":[122],"our":[123],"proposed":[124],"method":[125],"compare":[127],"it":[128],"methods":[131],"have":[133],"access":[134],"aligned":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":31},{"year":2021,"cited_by_count":68},{"year":2020,"cited_by_count":67},{"year":2019,"cited_by_count":46},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}