{"id":"https://openalex.org/W4391021757","doi":"https://doi.org/10.1109/asru57964.2023.10389621","title":"QUICKVC: A Lightweight VITS-Based Any-to-Many Voice Conversion Model using ISTFT for Faster Conversion","display_name":"QUICKVC: A Lightweight VITS-Based Any-to-Many Voice Conversion Model using ISTFT for Faster Conversion","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021757","doi":"https://doi.org/10.1109/asru57964.2023.10389621"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5027839955","display_name":"Houjian Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Houjian Guo","raw_affiliation_strings":["Interactive Robot Research Team, Guardian Robot Project,RIKEN,Japan","Interactive Robot Research Team, Guardian Robot Project, RIKEN, Japan","Graduate School of Engineering Science, Osaka University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Robot Research Team, Guardian Robot Project,RIKEN,Japan","institution_ids":["https://openalex.org/I4210144102"]},{"raw_affiliation_string":"Interactive Robot Research Team, Guardian Robot Project, RIKEN, Japan","institution_ids":[]},{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101905297","display_name":"Chaoran Liu","orcid":"https://orcid.org/0000-0003-3789-2981"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Chaoran Liu","raw_affiliation_strings":["Interactive Robot Research Team, Guardian Robot Project,RIKEN,Japan","Interactive Robot Research Team, Guardian Robot Project, RIKEN, Japan","Advanced Telecommunications Research Institute International, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Robot Research Team, Guardian Robot Project,RIKEN,Japan","institution_ids":["https://openalex.org/I4210144102"]},{"raw_affiliation_string":"Interactive Robot Research Team, Guardian Robot Project, RIKEN, Japan","institution_ids":[]},{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000037110","display_name":"Carlos Toshinori Ishi","orcid":"https://orcid.org/0000-0001-8130-1048"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I4210144102","display_name":"Wuhu Hit Robot Technology Research Institute","ror":"https://ror.org/049w4dp92","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144102"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Carlos Toshinori Ishi","raw_affiliation_strings":["Interactive Robot Research Team, Guardian Robot Project,RIKEN,Japan","Advanced Telecommunications Research Institute International, Japan","Interactive Robot Research Team, Guardian Robot Project, RIKEN, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Robot Research Team, Guardian Robot Project,RIKEN,Japan","institution_ids":["https://openalex.org/I4210144102"]},{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"Interactive Robot Research Team, Guardian Robot Project, RIKEN, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101425832","display_name":"Hiroshi Ishiguro","orcid":"https://orcid.org/0000-0002-0805-7648"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Ishiguro","raw_affiliation_strings":["Osaka University,Graduate School of Engineering Science,Japan","Graduate School of Engineering Science, Osaka University, Japan","Advanced Telecommunications Research Institute International, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University,Graduate School of Engineering Science,Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983000159263611,"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":0.987500011920929,"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":0.846301794052124},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6244934797286987},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6054113507270813},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5915356874465942},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5290257930755615},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5092719793319702},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.49024611711502075},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4629206657409668},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4311816096305847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3927009105682373},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09865489602088928}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.846301794052124},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6244934797286987},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6054113507270813},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5915356874465942},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5290257930755615},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5092719793319702},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.49024611711502075},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4629206657409668},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4311816096305847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3927009105682373},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09865489602088928},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1875842236","https://openalex.org/W2171019095","https://openalex.org/W2194775991","https://openalex.org/W2515028311","https://openalex.org/W2593414223","https://openalex.org/W2902070858","https://openalex.org/W2946200149","https://openalex.org/W2964243274","https://openalex.org/W2972667718","https://openalex.org/W2998572311","https://openalex.org/W3083423753","https://openalex.org/W3092028330","https://openalex.org/W3154451338","https://openalex.org/W3161695192","https://openalex.org/W3162427973","https://openalex.org/W3163568691","https://openalex.org/W3165478005","https://openalex.org/W3197659778","https://openalex.org/W3209059054","https://openalex.org/W3210530853","https://openalex.org/W4200225196","https://openalex.org/W4221152438","https://openalex.org/W4372260053","https://openalex.org/W4372270423","https://openalex.org/W6757817989","https://openalex.org/W6762533536","https://openalex.org/W6763832098","https://openalex.org/W6772349387","https://openalex.org/W6783867762","https://openalex.org/W6784299611","https://openalex.org/W6796464841","https://openalex.org/W6802527329"],"related_works":["https://openalex.org/W2039489009","https://openalex.org/W2120771489","https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4200596008","https://openalex.org/W596245619"],"abstract_inverted_index":{"With":[0],"the":[1,52,61,67,74,87,118,126,138],"development":[2],"of":[3,36,92],"automatic":[4],"speech":[5,94],"recognition":[6],"and":[7,21,81,96,121],"text-to-speech":[8],"technology,":[9],"high-quality":[10],"voice":[11,47],"conversion":[12,48],"can":[13,110],"be":[14],"achieved":[15],"by":[16],"extracting":[17],"source":[18],"content":[19,57],"information":[20,24,58],"target":[22],"speaker":[23],"to":[25,55,72,134],"reconstruct":[26],"waveforms.":[27],"However,":[28],"current":[29],"methods":[30,136],"still":[31],"require":[32],"improvement":[33],"in":[34,132],"terms":[35],"inference":[37,102],"speed.":[38],"In":[39],"this":[40],"study,":[41],"we":[42,65],"propose":[43],"a":[44],"lightweight":[45],"VITS-based":[46],"model":[49,54,89,109],"that":[50,107],"uses":[51],"HuBERT-Soft":[53],"extract":[56],"features.":[59],"Unlike":[60],"original":[62],"VITS":[63],"model,":[64],"use":[66],"inverse":[68],"short-time":[69],"Fourier":[70],"transform":[71],"replace":[73],"most":[75],"computationally":[76],"expensive":[77],"part.":[78],"Through":[79],"subjective":[80],"objective":[82],"experiments":[83],"on":[84,117,125],"synthesized":[85],"speech,":[86],"proposed":[88],"is":[90,98],"capable":[91],"natural":[93],"generation":[95],"it":[97],"very":[99],"efficient":[100],"at":[101,113],"time.":[103],"Experimental":[104],"results":[105],"show":[106],"our":[108],"generate":[111],"samples":[112],"over":[114,122],"5000":[115],"KHz":[116,124],"3090":[119],"GPU":[120],"250":[123],"i9-10900K":[127],"CPU,":[128],"achieving":[129],"faster":[130],"speed":[131],"comparison":[133],"baseline":[135],"using":[137],"same":[139],"hardware":[140],"configuration.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}