{"id":"https://openalex.org/W4224918934","doi":"https://doi.org/10.1109/icassp43922.2022.9747284","title":"Meta Talk: Learning To Data-Efficiently Generate Audio-Driven Lip-Synchronized Talking Face With High Definition","display_name":"Meta Talk: Learning To Data-Efficiently Generate Audio-Driven Lip-Synchronized Talking Face With High Definition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224918934","doi":"https://doi.org/10.1109/icassp43922.2022.9747284"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747284","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":"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/A5100385416","display_name":"Yuhan Zhang","orcid":"https://orcid.org/0000-0001-8579-4943"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhan Zhang","raw_affiliation_strings":["Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082709206","display_name":"Weihua He","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihua He","raw_affiliation_strings":["Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100780135","display_name":"Minglei Li","orcid":"https://orcid.org/0000-0002-1427-3507"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minglei Li","raw_affiliation_strings":["Huawei Technologies Co. Ltd.,Language &#x0026; Speech Innovation Lab,China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd.,Language &#x0026; Speech Innovation Lab,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012753527","display_name":"Kun Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Tian","raw_affiliation_strings":["Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808892","display_name":"Ziyang Zhang","orcid":"https://orcid.org/0000-0001-9136-5416"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Zhang","raw_affiliation_strings":["Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101523656","display_name":"Jie Cheng","orcid":"https://orcid.org/0000-0002-6171-4651"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Cheng","raw_affiliation_strings":["Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808569","display_name":"Yaoyuan Wang","orcid":"https://orcid.org/0000-0003-1060-4898"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoyuan Wang","raw_affiliation_strings":["Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073845819","display_name":"Jianxing Liao","orcid":"https://orcid.org/0009-0002-5474-4163"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxing Liao","raw_affiliation_strings":["Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co. Ltd.,Advanced Computing and Storage Lab,China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Advanced Computing and Storage Lab, Huawei Technologies Co. Ltd., China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100385416"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":0.4178,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.69375444,"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":"4848","last_page":"4852"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11448","display_name":"Face recognition and analysis","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9975000023841858,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9886000156402588,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8277229070663452},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.6303920745849609},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5168052911758423},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5109666585922241},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5088015198707581},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4833049774169922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44666749238967896},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.43329429626464844},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.39891788363456726},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3811763823032379},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.38104838132858276},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3605160713195801},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.17876902222633362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8277229070663452},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.6303920745849609},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5168052911758423},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5109666585922241},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5088015198707581},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4833049774169922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44666749238967896},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.43329429626464844},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.39891788363456726},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3811763823032379},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.38104838132858276},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3605160713195801},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.17876902222633362},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747284","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":[{"score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2017107803","https://openalex.org/W2105649179","https://openalex.org/W2107037917","https://openalex.org/W2803705807","https://openalex.org/W2890952074","https://openalex.org/W2944294033","https://openalex.org/W2963073614","https://openalex.org/W2964449965","https://openalex.org/W3081492798","https://openalex.org/W3087121792","https://openalex.org/W3101631197","https://openalex.org/W3195529437","https://openalex.org/W3202128205","https://openalex.org/W3204680331","https://openalex.org/W6729966448","https://openalex.org/W6754392867","https://openalex.org/W6776650102","https://openalex.org/W6800213368"],"related_works":["https://openalex.org/W2048402902","https://openalex.org/W1863533157","https://openalex.org/W2103413230","https://openalex.org/W2098934641","https://openalex.org/W2792033502","https://openalex.org/W2170815394","https://openalex.org/W3043119899","https://openalex.org/W4382560817","https://openalex.org/W4234540277","https://openalex.org/W2143802570"],"abstract_inverted_index":{"Audio-driven":[0],"talking":[1,4,36,51,181],"face,":[2],"driving":[3],"face":[5,37,52,68,107,113,130,164,179,182],"by":[6,32,71,126],"audio,":[7],"has":[8,194],"received":[9],"considerable":[10],"attention":[11],"in":[12,20,74,198,205],"multi-modal":[13],"learning":[14],"due":[15],"to":[16,62,138,145,166],"its":[17],"widespread":[18],"use":[19],"virtual":[21],"reality.":[22],"However,":[23],"long-time":[24],"recording":[25],"of":[26,88,149,185],"target":[27,60,105,129],"high-quality":[28],"video":[29,61,69,124,131],"is":[30,154],"needed":[31],"most":[33],"existing":[34,211],"audio-driven":[35,50,136],"studies,":[38],"which":[39,55],"significantly":[40],"increases":[41],"customization":[42],"costs.":[43],"This":[44],"paper":[45],"proposes":[46],"a":[47,58,168,172],"novel":[48],"data-efficient":[49],"generation":[53],"method,":[54],"uses":[56],"just":[57],"short":[59],"produce":[63],"both":[64],"lip-synchronized":[65],"and":[66,91,93,143,159,202],"high-definition":[67,199],"driven":[70],"arbitrary":[72],"audio":[73,158],"the":[75,103,133,147,177,191,195,210],"wild.":[76],"Current":[77],"methods":[78],"suffer":[79],"from":[80],"many":[81],"problems,":[82],"such":[83],"as":[84],"low":[85],"definition,":[86],"asynchronization":[87],"lip":[89,206],"movement":[90],"voice,":[92],"intense":[94],"demands":[95],"for":[96,98],"videos":[97],"training.":[99],"In":[100],"this":[101],"work,":[102],"original":[104],"character\u2019s":[106],"images":[108],"are":[109],"decomposed":[110],"into":[111,180],"3D":[112],"model":[114,137],"parameters":[115,165],"including":[116],"expression,":[117],"geometry,":[118],"illumination,":[119],"etc.":[120],"Then,":[121],"low-definition":[122],"pseudo":[123],"generated":[125],"an":[127,157],"adapted":[128],"bridges":[132],"powerful":[134],"pre-trained":[135],"our":[139],"audio-to-expression":[140],"transformation":[141],"network":[142,175],"help":[144],"transfer":[146],"ability":[148],"audio-identity":[150],"disentanglement.":[151],"The":[152],"expression":[153],"replaced":[155],"via":[156],"then":[160],"combined":[161],"with":[162,209],"other":[163],"render":[167],"synthetic":[169,178],"face.":[170],"Finally,":[171],"neural":[173],"rendering":[174],"translates":[176],"without":[183],"loss":[184],"definition.":[186],"Experimental":[187],"results":[188],"show":[189],"that":[190],"proposed":[192],"method":[193],"best":[196],"performance":[197,204],"image":[200],"quality,":[201],"comparable":[203],"synchronization":[207],"compared":[208],"state-of-the-art":[212],"methods.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}
