{"id":"https://openalex.org/W4224926225","doi":"https://doi.org/10.1109/icassp43922.2022.9747427","title":"VCVTS: Multi-Speaker Video-to-Speech Synthesis Via Cross-Modal Knowledge Transfer from Voice Conversion","display_name":"VCVTS: Multi-Speaker Video-to-Speech Synthesis Via Cross-Modal Knowledge Transfer from Voice Conversion","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224926225","doi":"https://doi.org/10.1109/icassp43922.2022.9747427"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747427","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5068726270","display_name":"Disong Wang","orcid":"https://orcid.org/0000-0001-8481-6880"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Disong Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR, China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736420","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"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":"Shan Yang","raw_affiliation_strings":["Tencent AI lab,China","Tencent AI lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","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":["Tencent AI lab,China","Tencent AI lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR, China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"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":"Dong Yu","raw_affiliation_strings":["Tencent AI lab,China","Tencent AI lab, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI lab,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR, China","Centre for Perceptual and Interactive Intelligence, Hong Kong SAR, China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence, Hong Kong SAR, China","institution_ids":[]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0303,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.88791088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7252","last_page":"7256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.7922663688659668},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7278855443000793},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6104754209518433},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5738113522529602},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5543946027755737},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4775208532810211},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46300485730171204},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.4519363343715668},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.44693949818611145},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4126269817352295},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3763417601585388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36689895391464233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922663688659668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7278855443000793},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6104754209518433},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5738113522529602},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5543946027755737},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4775208532810211},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46300485730171204},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.4519363343715668},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.44693949818611145},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4126269817352295},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3763417601585388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36689895391464233},{"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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747427","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1862426464","https://openalex.org/W2015143272","https://openalex.org/W2067295501","https://openalex.org/W2068056889","https://openalex.org/W2115252128","https://openalex.org/W2120847449","https://openalex.org/W2146444479","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2293856338","https://openalex.org/W2516001803","https://openalex.org/W2585824449","https://openalex.org/W2625027024","https://openalex.org/W2739009240","https://openalex.org/W2765407302","https://openalex.org/W2842511635","https://openalex.org/W2887437849","https://openalex.org/W2963019222","https://openalex.org/W2963936489","https://openalex.org/W2964352155","https://openalex.org/W2972359262","https://openalex.org/W2972563022","https://openalex.org/W2979476256","https://openalex.org/W3015338123","https://openalex.org/W3016011581","https://openalex.org/W3027324582","https://openalex.org/W3035626590","https://openalex.org/W3036928441","https://openalex.org/W3095361818","https://openalex.org/W3096650361","https://openalex.org/W3097777922","https://openalex.org/W3101481642","https://openalex.org/W3157840621","https://openalex.org/W3160305627","https://openalex.org/W3197659778","https://openalex.org/W4206204999","https://openalex.org/W4297808394","https://openalex.org/W6631190155","https://openalex.org/W6677618333","https://openalex.org/W6734491695","https://openalex.org/W6745136726","https://openalex.org/W6769196770","https://openalex.org/W6779459370","https://openalex.org/W6794378236","https://openalex.org/W7042829694"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2206035908","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148"],"abstract_inverted_index":{"Though":[0],"significant":[1],"progress":[2],"has":[3],"been":[4],"made":[5],"for":[6,64,116],"speaker-dependent":[7],"Video-to-Speech":[8],"(VTS)":[9],"synthesis,":[10],"little":[11],"attention":[12],"is":[13,62,185],"devoted":[14],"to":[15,23,70,79,84,103,109,113,135,139],"multi-speaker":[16,42,106],"VTS":[17,43,107,122],"that":[18],"can":[19,95,157],"map":[20],"silent":[21,111],"video":[22,112],"speech,":[24],"while":[25],"allowing":[26],"flexible":[27],"control":[28,141],"of":[29,68,89,101,128,145,153],"speaker":[30,133,137,143,180],"identity,":[31],"all":[32],"in":[33,160,171],"a":[34,40,80,105,132],"single":[35],"system.":[36],"This":[37],"paper":[38],"proposes":[39],"novel":[41],"system":[44,108,123],"based":[45],"on":[46],"cross-modal":[47],"knowledge":[48],"transfer":[49],"from":[50],"voice":[51],"conversion":[52],"(VC),":[53],"where":[54],"vector":[55],"quantization":[56],"with":[57,175],"contrastive":[58],"predictive":[59],"coding":[60],"(VQCPC)":[61],"used":[63],"the":[65,86,98,126,142,151],"content":[66,99],"encoder":[67,100,134],"VC":[69,102,129],"derive":[71],"discrete":[72],"phoneme-like":[73],"acoustic":[74,90,114],"units,":[75],"which":[76,156],"are":[77],"transferred":[78],"Lip-to-Index":[81],"(Lip2Ind)":[82],"network":[83,94],"infer":[85],"index":[87],"sequence":[88],"units.":[91],"The":[92,121],"Lip2Ind":[93],"then":[96],"substitute":[97],"form":[104],"convert":[110],"units":[115],"reconstructing":[117],"accurate":[118],"spoken":[119],"content.":[120],"also":[124],"inherits":[125],"advantages":[127],"by":[130],"using":[131],"produce":[136],"representations":[138],"effectively":[140],"identity":[144],"generated":[146],"speech.":[147],"Extensive":[148],"evaluations":[149],"verify":[150],"effectiveness":[152],"proposed":[154],"approach,":[155],"be":[158],"applied":[159],"both":[161],"constrained":[162],"vocabulary":[163,166],"and":[164,179],"open":[165],"conditions,":[167],"achieving":[168],"state-of-the-art":[169],"performance":[170],"generating":[172],"high-quality":[173],"speech":[174],"high":[176],"naturalness,":[177],"intelligibility":[178],"similarity.":[181],"Our":[182],"demo":[183],"page":[184],"released":[186],"here1.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
