{"id":"https://openalex.org/W3080610628","doi":"https://doi.org/10.1145/3404555.3404627","title":"Voice Conversion towards Arbitrary Speakers With Limited Data","display_name":"Voice Conversion towards Arbitrary Speakers With Limited Data","publication_year":2020,"publication_date":"2020-04-23","ids":{"openalex":"https://openalex.org/W3080610628","doi":"https://doi.org/10.1145/3404555.3404627","mag":"3080610628"},"language":"en","primary_location":{"id":"doi:10.1145/3404555.3404627","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404555.3404627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","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/A5100762200","display_name":"Ying Zhang","orcid":"https://orcid.org/0000-0001-7581-7187"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Zhang","raw_affiliation_strings":["Tsinghua University, Haidian, Beijing"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Haidian, Beijing","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447801","display_name":"Wenjun Zhang","orcid":"https://orcid.org/0000-0001-7973-8769"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Zhang","raw_affiliation_strings":["Tsinghua University, Haidian, Beijing"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Haidian, Beijing","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039153635","display_name":"Dandan Song","orcid":"https://orcid.org/0000-0002-7239-6900"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dandan Song","raw_affiliation_strings":["TsingMicro Tech, Haidian, Beijing"],"affiliations":[{"raw_affiliation_string":"TsingMicro Tech, Haidian, Beijing","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100762200"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09586096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"104","last_page":"108"},"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":0.9976000189781189,"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":0.9922000169754028,"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":0.7803822755813599},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7566757202148438},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6500647068023682},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5760655403137207},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5548685789108276},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5056068897247314},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4930679500102997},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47213250398635864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3947495222091675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33986249566078186},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1306660771369934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803822755813599},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7566757202148438},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6500647068023682},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5760655403137207},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5548685789108276},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5056068897247314},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4930679500102997},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47213250398635864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3947495222091675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33986249566078186},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1306660771369934},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3404555.3404627","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3404555.3404627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2112021726","https://openalex.org/W2150769028","https://openalex.org/W2156142001","https://openalex.org/W2187089797","https://openalex.org/W2294351487","https://openalex.org/W2395403337","https://openalex.org/W2471520273","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2806000759","https://openalex.org/W2808631503","https://openalex.org/W2888922217","https://openalex.org/W2972359262","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,25,31,42],"towards":[2,32],"a":[3,7,22,39,56,63,91,155],"specific":[4],"speaker":[5,57,66,96,160],"requires":[6],"large":[8],"number":[9],"of":[10,62,80],"target":[11,65,82,159],"speaker's":[12],"utterances,":[13],"which":[14,28],"is":[15,45],"expensive":[16],"in":[17],"practice.":[18],"This":[19],"paper":[20],"proposes":[21],"speaker-adaptive":[23],"voice":[24,30,41,79],"(SAVC)":[26],"system,":[27],"accomplishes":[29],"arbitrary":[33],"speakers":[34,53],"with":[35],"limited":[36],"data.":[37],"First,":[38],"multi-speaker":[40],"(MSVC)":[43],"model":[44,74,126,143,150],"trained":[46],"to":[47,69,76,105,111,158],"learn":[48,77],"the":[49,72,78,81,85,107,123,133,141,147],"shared":[50],"information":[51],"between":[52],"and":[54,95],"build":[55],"latent":[58],"space.":[59],"Second,":[60],"utterances":[61],"new":[64],"are":[67,103,119],"used":[68],"fine":[70],"tune":[71],"MSVC":[73,125,142],"aiming":[75],"speaker.":[83],"In":[84,109],"two":[86,115],"steps,":[87],"phonetic":[88],"posteriorgrams":[89],"(PPGs),":[90],"speaker-independent":[92],"linguistic":[93],"feature,":[94],"embeddings":[97],"such":[98],"as":[99],"i-vector":[100],"or":[101,127],"x-vector":[102,153],"encoded":[104],"train":[106],"model.":[108],"order":[110],"achieve":[112],"better":[113],"results,":[114],"different":[116],"adaptive":[117,137],"approaches":[118,138],"explored:":[120],"adaptation":[121],"on":[122,152],"whole":[124,148],"additional":[128],"linear-hidden":[129],"layers":[130],"(AHL).":[131],"As":[132],"results":[134],"show,":[135],"both":[136],"significantly":[139],"outperform":[140],"without":[144],"adaptation.":[145],"Besides,":[146],"adapted":[149],"based":[151],"gets":[154],"higher":[156],"similarity":[157],"within":[161],"10":[162],"utterances.":[163]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}