{"id":"https://openalex.org/W4225984289","doi":"https://doi.org/10.1007/978-3-030-87664-7_8","title":"Talking Faces: Audio-to-Video Face Generation","display_name":"Talking Faces: Audio-to-Video Face Generation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4225984289","doi":"https://doi.org/10.1007/978-3-030-87664-7_8"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-87664-7_8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-87664-7_8","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-87664-7_8.pdf","source":{"id":"https://openalex.org/S4210181928","display_name":"Advances in computer vision and pattern recognition","issn_l":"2191-6586","issn":["2191-6586","2191-6594"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Computer Vision and Pattern Recognition","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-87664-7_8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100427475","display_name":"Yuxin Wang","orcid":"https://orcid.org/0000-0002-5133-3978"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Wang","raw_affiliation_strings":["SenseTime Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043375205","display_name":"Linsen Song","orcid":"https://orcid.org/0000-0003-0817-2600"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linsen Song","raw_affiliation_strings":["NLPR, CASIA, Beijing, China"],"affiliations":[{"raw_affiliation_string":"NLPR, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000896822","display_name":"Wayne Wu","orcid":"https://orcid.org/0000-0002-1364-8151"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wayne Wu","raw_affiliation_strings":["SenseTime Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657544","display_name":"Chen Qian","orcid":"https://orcid.org/0000-0002-8761-5563"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Qian","raw_affiliation_strings":["SenseTime Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112749024","display_name":"Ran He","orcid":"https://orcid.org/0000-0002-3807-991X"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran He","raw_affiliation_strings":["NLPR, CASIA, Beijing, China"],"affiliations":[{"raw_affiliation_string":"NLPR, CASIA, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005626854","display_name":"Chen Change Loy","orcid":"https://orcid.org/0000-0001-5345-1591"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Chen Change Loy","raw_affiliation_strings":["S-Lab, Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"S-Lab, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005626854"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.4197,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69699956,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"163","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9997000098228455,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9997000098228455,"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/T11448","display_name":"Face recognition and analysis","score":0.9997000098228455,"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":0.980400025844574,"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":0.7382996082305908},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6865209341049194},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6377713680267334},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5611891746520996},{"id":"https://openalex.org/keywords/teleconference","display_name":"Teleconference","score":0.5583418011665344},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.49012336134910583},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.43062078952789307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40691447257995605},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39977848529815674},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12914744019508362},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10717609524726868}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7382996082305908},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6865209341049194},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6377713680267334},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5611891746520996},{"id":"https://openalex.org/C126669455","wikidata":"https://www.wikidata.org/wiki/Q1630941","display_name":"Teleconference","level":2,"score":0.5583418011665344},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.49012336134910583},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.43062078952789307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40691447257995605},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39977848529815674},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12914744019508362},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10717609524726868},{"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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-87664-7_8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-87664-7_8","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-87664-7_8.pdf","source":{"id":"https://openalex.org/S4210181928","display_name":"Advances in computer vision and pattern recognition","issn_l":"2191-6586","issn":["2191-6586","2191-6594"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Computer Vision and Pattern Recognition","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-87664-7_8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-87664-7_8","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-87664-7_8.pdf","source":{"id":"https://openalex.org/S4210181928","display_name":"Advances in computer vision and pattern recognition","issn_l":"2191-6586","issn":["2191-6586","2191-6594"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Computer Vision and Pattern Recognition","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225984289.pdf","grobid_xml":"https://content.openalex.org/works/W4225984289.grobid-xml"},"referenced_works_count":99,"referenced_works":["https://openalex.org/W34110307","https://openalex.org/W204612701","https://openalex.org/W1569907127","https://openalex.org/W2004068758","https://openalex.org/W2004789217","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2030931454","https://openalex.org/W2060352302","https://openalex.org/W2071441136","https://openalex.org/W2080277992","https://openalex.org/W2082942761","https://openalex.org/W2083792893","https://openalex.org/W2084235337","https://openalex.org/W2089192201","https://openalex.org/W2096733369","https://openalex.org/W2106723645","https://openalex.org/W2107037917","https://openalex.org/W2112796928","https://openalex.org/W2114588272","https://openalex.org/W2115402659","https://openalex.org/W2120420721","https://openalex.org/W2128173845","https://openalex.org/W2133665775","https://openalex.org/W2134963900","https://openalex.org/W2146991130","https://openalex.org/W2147885303","https://openalex.org/W2152754093","https://openalex.org/W2160634117","https://openalex.org/W2162598851","https://openalex.org/W2169931729","https://openalex.org/W2180648442","https://openalex.org/W2186222003","https://openalex.org/W2237250383","https://openalex.org/W2265959009","https://openalex.org/W2295661697","https://openalex.org/W2301937176","https://openalex.org/W2398381847","https://openalex.org/W2431101926","https://openalex.org/W2468212864","https://openalex.org/W2519156253","https://openalex.org/W2551572271","https://openalex.org/W2572640303","https://openalex.org/W2594690981","https://openalex.org/W2603777577","https://openalex.org/W2604379605","https://openalex.org/W2737067721","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2745771616","https://openalex.org/W2763695663","https://openalex.org/W2803193013","https://openalex.org/W2804619907","https://openalex.org/W2808631503","https://openalex.org/W2883183894","https://openalex.org/W2883861033","https://openalex.org/W2884460600","https://openalex.org/W2895749211","https://openalex.org/W2903093723","https://openalex.org/W2904868363","https://openalex.org/W2912459656","https://openalex.org/W2914217321","https://openalex.org/W2943322963","https://openalex.org/W2944294033","https://openalex.org/W2952552312","https://openalex.org/W2960274051","https://openalex.org/W2962770929","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2964559396","https://openalex.org/W2969985801","https://openalex.org/W2979894294","https://openalex.org/W2981087920","https://openalex.org/W3006295631","https://openalex.org/W3034211329","https://openalex.org/W3035169015","https://openalex.org/W3035574324","https://openalex.org/W3036198682","https://openalex.org/W3081492798","https://openalex.org/W3089177030","https://openalex.org/W3097792222","https://openalex.org/W3099284785","https://openalex.org/W3101531717","https://openalex.org/W3101631197","https://openalex.org/W3106370837","https://openalex.org/W3107666850","https://openalex.org/W3127511859","https://openalex.org/W3154807520","https://openalex.org/W3174658753","https://openalex.org/W3174763799","https://openalex.org/W3180770160","https://openalex.org/W3186090335","https://openalex.org/W3192148059","https://openalex.org/W3211147706","https://openalex.org/W6600007113","https://openalex.org/W6600120041","https://openalex.org/W6823694774","https://openalex.org/W6828950989"],"related_works":["https://openalex.org/W2152590879","https://openalex.org/W81679406","https://openalex.org/W64836642","https://openalex.org/W2003424743","https://openalex.org/W99640392","https://openalex.org/W2508779976","https://openalex.org/W2514526842","https://openalex.org/W2385859805","https://openalex.org/W2893597338","https://openalex.org/W2530972254"],"abstract_inverted_index":{"Abstract":[0],"Talking":[1],"face":[2,10,50,58,72,104],"generation":[3],"aims":[4],"at":[5],"synthesizing":[6],"coherent":[7],"and":[8,30,38,74,88,114,125],"realistic":[9],"sequences":[11],"given":[12],"an":[13,97],"input":[14],"speech.":[15],"The":[16,33],"task":[17],"enjoys":[18],"a":[19],"wide":[20],"spectrum":[21],"of":[22,35,71,91,99],"downstream":[23],"applications,":[24],"such":[25],"as":[26],"teleconferencing,":[27],"movie":[28],"dubbing,":[29],"virtual":[31],"assistant.":[32],"emergence":[34],"deep":[36],"learning":[37],"cross-modality":[39],"research":[40,54],"has":[41],"led":[42],"to":[43,65,77],"many":[44],"interesting":[45],"works":[46],"that":[47],"address":[48],"talking":[49,57,103],"generation.":[51,105],"Despite":[52],"great":[53],"efforts":[55],"in":[56,102,128],"generation,":[59],"the":[60,66,75,86,92],"problem":[61],"remains":[62],"challenging":[63],"due":[64],"need":[67],"for":[68],"fine-grained":[69],"control":[70],"components":[73],"generalization":[76],"arbitrary":[78],"sentences.":[79],"In":[80,106],"this":[81,129],"chapter,":[82],"we":[83,95,108,118],"first":[84],"discuss":[85,119],"definition":[87],"underlying":[89],"challenges":[90],"problem.":[93],"Then,":[94],"present":[96],"overview":[98],"recent":[100],"progress":[101],"addition,":[107],"introduce":[109],"some":[110],"widely":[111],"used":[112],"datasets":[113],"performance":[115],"metrics.":[116],"Finally,":[117],"open":[120],"questions,":[121],"potential":[122],"future":[123],"directions,":[124],"ethical":[126],"considerations":[127],"task.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}