{"id":"https://openalex.org/W4319587015","doi":"https://doi.org/10.1109/iscslp57327.2022.10037585","title":"AdaVITS: Tiny VITS for Low Computing Resource Speaker Adaptation","display_name":"AdaVITS: Tiny VITS for Low Computing Resource Speaker Adaptation","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319587015","doi":"https://doi.org/10.1109/iscslp57327.2022.10037585"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037585","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100722258","display_name":"Kun Song","orcid":"https://orcid.org/0000-0001-6110-2770"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Song","raw_affiliation_strings":["Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064426059","display_name":"Heyang Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heyang Xue","raw_affiliation_strings":["Northwestern Polytechnical University,School of Software,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Software,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115547209","display_name":"Xinsheng Wang","orcid":"https://orcid.org/0000-0002-7528-4621"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064364353","display_name":"Jian Cong","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cong","raw_affiliation_strings":["Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060467975","display_name":"Yongmao Zhang","orcid":"https://orcid.org/0009-0000-0526-5778"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongmao Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611540","display_name":"Bing Yang","orcid":"https://orcid.org/0000-0003-3515-0642"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Yang","raw_affiliation_strings":["Cloud and Smart Industries Group, Tencent Technology Co., Ltd.,China","Cloud and Smart Industries Group, Tencent Technology Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud and Smart Industries Group, Tencent Technology Co., Ltd.,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Cloud and Smart Industries Group, Tencent Technology Co., Ltd., China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103477851","display_name":"Xiong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiong Zhang","raw_affiliation_strings":["Cloud and Smart Industries Group, Tencent Technology Co., Ltd.,China","Cloud and Smart Industries Group, Tencent Technology Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud and Smart Industries Group, Tencent Technology Co., Ltd.,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Cloud and Smart Industries Group, Tencent Technology Co., Ltd., China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Cloud and Smart Industries Group, Tencent Technology Co., Ltd.,China","Cloud and Smart Industries Group, Tencent Technology Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud and Smart Industries Group, Tencent Technology Co., Ltd.,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Cloud and Smart Industries Group, Tencent Technology Co., Ltd., China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6229,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69128015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"323"},"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":0.9943000078201294,"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":0.7638152837753296},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.6391127109527588},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.6218903660774231},{"id":"https://openalex.org/keywords/computational-resource","display_name":"Computational resource","score":0.6067487597465515},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.58692866563797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5853400230407715},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.5547295808792114},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.45589685440063477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36312007904052734},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31665027141571045},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.143934965133667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7638152837753296},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.6391127109527588},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.6218903660774231},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.6067487597465515},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.58692866563797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5853400230407715},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5547295808792114},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.45589685440063477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36312007904052734},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31665027141571045},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.143934965133667},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037585","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2747329762","https://openalex.org/W2963609956","https://openalex.org/W2972359262","https://openalex.org/W3095035471","https://openalex.org/W3096159803","https://openalex.org/W3096408984","https://openalex.org/W3097728852","https://openalex.org/W3103104054","https://openalex.org/W3128910262","https://openalex.org/W3144035034","https://openalex.org/W3160919572","https://openalex.org/W3197478142","https://openalex.org/W3198869563","https://openalex.org/W3207340675","https://openalex.org/W3213227271","https://openalex.org/W6638523607","https://openalex.org/W6727697161","https://openalex.org/W6748588790","https://openalex.org/W6755135894","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6778823374","https://openalex.org/W6779709467","https://openalex.org/W6779711495","https://openalex.org/W6785954764","https://openalex.org/W6790220310","https://openalex.org/W6796464841","https://openalex.org/W6802566663","https://openalex.org/W6803159591"],"related_works":["https://openalex.org/W2229588459","https://openalex.org/W2374430960","https://openalex.org/W2375485824","https://openalex.org/W4235807378","https://openalex.org/W120571988","https://openalex.org/W4249702239","https://openalex.org/W2742629360","https://openalex.org/W1512399864","https://openalex.org/W2047754121","https://openalex.org/W2499978181"],"abstract_inverted_index":{"Speaker":[0],"adaptation":[1,73,187],"in":[2,105,185],"text-to-speech":[3],"synthesis":[4],"(TTS)":[5],"is":[6,74,95,103,111,141],"to":[7,13,15,42,97,113,121,130,173],"fine-tune":[8],"a":[9,60,162],"pre-trained":[10],"TTS":[11,64],"model":[12,52,169,191],"adapt":[14],"new":[16],"target":[17],"speakers":[18],"with":[19,143,148,188],"limited":[20],"data.":[21],"While":[22],"much":[23],"effort":[24],"has":[25,33],"been":[26,34],"conducted":[27],"towards":[28],"this":[29,58],"task,":[30],"seldom":[31],"work":[32],"performed":[35],"for":[36,68,166],"low":[37,69],"computational":[38,55,82,133,196],"resource":[39,71],"scenarios":[40],"due":[41],"the":[43,47,50,79,99,106,115,123,126,132,136,149,153,168],"challenges":[44],"raised":[45],"by":[46,152],"requirement":[48],"of":[49,84,125,135],"lightweight":[51],"and":[53,81,182,193],"less":[54],"complexity.":[56,197],"In":[57],"paper,":[59],"tiny":[61],"VITS-based":[62],"[1]":[63],"model,":[65,155],"named":[66],"AdaVITS,":[67],"computing":[70],"speaker":[72,186],"proposed.":[75],"To":[76,146],"effectively":[77],"reduce":[78,122,131],"parameters":[80,124,192],"complexity":[83,134],"VITS,":[85],"an":[86],"inverse":[87],"short-time":[88],"Fourier":[89],"transform":[90],"(iSTFT)-based":[91],"wave":[92],"construction":[93],"decoder":[94,101],"proposed":[96],"replace":[98],"upsampling-based":[100],"which":[102],"resource-consuming":[104],"original":[107],"VITS.":[108],"Besides,":[109],"NanoFlow":[110],"introduced":[112],"share":[114],"density":[116],"estimate":[117],"across":[118],"flow":[119],"blocks":[120],"prior":[127],"encoder.":[128],"Furthermore,":[129],"textual":[137],"encoder,":[138],"scaled-dot":[139],"attention":[140],"replaced":[142],"linear":[144],"attention.":[145],"deal":[147],"instability":[150],"caused":[151],"simplified":[154],"we":[156],"use":[157],"phonetic":[158],"posteriorgram":[159],"(PPG)":[160],"as":[161],"frame-level":[163],"linguistic":[164],"feature":[165],"supervising":[167],"process":[170],"from":[171],"phoneme":[172],"spectrum.":[174],"Experiments":[175],"show":[176],"that":[177],"AdaVITS":[178],"can":[179],"generate":[180],"stable":[181],"natural":[183],"speech":[184],"8.":[189],"97M":[190],"0.72":[194],"GFlops":[195],"<sup":[198],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[199],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}