{"id":"https://openalex.org/W4400948778","doi":"https://doi.org/10.1145/3672919.3672988","title":"Cross-lingual voice conversion based on F0 multi-scale modeling with VITS","display_name":"Cross-lingual voice conversion based on F0 multi-scale modeling with VITS","publication_year":2024,"publication_date":"2024-03-01","ids":{"openalex":"https://openalex.org/W4400948778","doi":"https://doi.org/10.1145/3672919.3672988"},"language":"en","primary_location":{"id":"doi:10.1145/3672919.3672988","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672919.3672988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 3rd International Conference on Cyber Security, Artificial Intelligence and Digital Economy","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/A5101617241","display_name":"Danyang Cao","orcid":"https://orcid.org/0000-0002-9779-9466"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Danyang Cao","raw_affiliation_strings":["School of information and technology, North China University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-9779-9466","affiliations":[{"raw_affiliation_string":"School of information and technology, North China University of Technology, China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111267386","display_name":"Zeyi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyi Zhang","raw_affiliation_strings":["School of Information and Technology, North China University of Technology, China"],"raw_orcid":"https://orcid.org/0009-0004-5529-5894","affiliations":[{"raw_affiliation_string":"School of Information and Technology, North China University of Technology, China","institution_ids":["https://openalex.org/I1456306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101617241"],"corresponding_institution_ids":["https://openalex.org/I1456306"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09187508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"375","last_page":"379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9456999897956848,"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":0.7173954248428345},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.560429573059082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5159857869148254},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32664093375205994},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06042596697807312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7173954248428345},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.560429573059082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5159857869148254},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32664093375205994},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06042596697807312},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3672919.3672988","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3672919.3672988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 3rd International Conference on Cyber Security, Artificial Intelligence and Digital Economy","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":16,"referenced_works":["https://openalex.org/W59075858","https://openalex.org/W2111550316","https://openalex.org/W2123808477","https://openalex.org/W2161476805","https://openalex.org/W2938583109","https://openalex.org/W2940620867","https://openalex.org/W3083423753","https://openalex.org/W3149794337","https://openalex.org/W3165478005","https://openalex.org/W3197659778","https://openalex.org/W4288391450","https://openalex.org/W4307537044","https://openalex.org/W4311000453","https://openalex.org/W4383173727","https://openalex.org/W4387559737","https://openalex.org/W6676626839"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"This":[0,127],"paper":[1],"introduces":[2],"a":[3,68,164],"cross-lingual":[4,37,94,138],"voice":[5,30,40,124],"conversion":[6,139],"technology":[7],"that":[8],"utilizes":[9],"an":[10,33,43,99],"F0":[11,100,158],"predictor":[12,101,159],"for":[13,92,102],"multi-scale":[14,103],"modeling":[15,104],"of":[16,51,78,85,105,121,148,156,166,178],"the":[17,23,39,49,55,75,79,82,86,109,118,122,132,146,154,157,161,176,179],"fundamental":[18,110],"frequency":[19,111],"(f0).":[20],"Based":[21],"on":[22,131],"VITS":[24],"architecture,":[25],"this":[26,62,113],"method":[27,181],"achieves":[28,137],"high-quality":[29],"generation":[31],"through":[32],"end-to-end":[34],"approach.":[35],"In":[36],"conversion,":[38],"often":[41],"carries":[42],"unnatural":[44],"foreign":[45,149],"accent":[46,84,119],"due":[47],"to":[48,107,116],"involvement":[50],"different":[52],"languages":[53,142],"in":[54,160],"source":[56,87,123],"and":[57,143,173],"target":[58],"voices.":[59],"To":[60,151],"address":[61],"issue,":[63],"Whisper":[64],"is":[65,90,182],"introduced":[66],"as":[67],"content":[69,77],"extraction":[70],"tool":[71],"aimed":[72],"at":[73],"capturing":[74],"detailed":[76],"speech,":[80],"including":[81],"specific":[83],"voice,":[88],"which":[89],"crucial":[91],"efficient":[93],"conversion.":[95,126],"Furthermore,":[96],"by":[97],"employing":[98],"f0":[106],"predict":[108],"contour,":[112],"strategy":[114],"helps":[115],"retain":[117],"characteristics":[120],"during":[125],"research,":[128],"trained":[129],"solely":[130],"VCTK":[133],"English":[134],"dataset,":[135],"effectively":[136],"across":[140],"various":[141],"significantly":[144],"reduces":[145],"impact":[147],"accents.":[150],"further":[152],"explore":[153],"contribution":[155],"proposed":[162,180],"model,":[163],"series":[165],"ablation":[167],"experiments":[168],"were":[169],"designed.":[170],"Through":[171],"objective":[172],"subjective":[174],"evaluations,":[175],"effectiveness":[177],"demonstrated.":[183]},"counts_by_year":[],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}