{"id":"https://openalex.org/W4323825009","doi":"https://doi.org/10.1109/iceic57457.2023.10049847","title":"Audio-to-Facial Landmarks Generator for Talking Face Video Synthesis","display_name":"Audio-to-Facial Landmarks Generator for Talking Face Video Synthesis","publication_year":2023,"publication_date":"2023-02-05","ids":{"openalex":"https://openalex.org/W4323825009","doi":"https://doi.org/10.1109/iceic57457.2023.10049847"},"language":"en","primary_location":{"id":"doi:10.1109/iceic57457.2023.10049847","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceic57457.2023.10049847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Electronics, Information, and Communication (ICEIC)","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/A5028893407","display_name":"Dasol Jeong","orcid":null},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Dasol Jeong","raw_affiliation_strings":["Chung-Ang University,Department of Image,Seoul,Korea","Department of Image, Chung-Ang University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Image,Seoul,Korea","institution_ids":["https://openalex.org/I67900169"]},{"raw_affiliation_string":"Department of Image, Chung-Ang University, Seoul, Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025713205","display_name":"Injae Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Injae Lee","raw_affiliation_strings":["Chung-Ang University,Department of Image,Seoul,Korea","Department of Image, Chung-Ang University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Image,Seoul,Korea","institution_ids":["https://openalex.org/I67900169"]},{"raw_affiliation_string":"Department of Image, Chung-Ang University, Seoul, Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013926864","display_name":"Joonki Paik","orcid":"https://orcid.org/0000-0002-8593-7155"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonki Paik","raw_affiliation_strings":["Chung-Ang University,Department of Image,Seoul,Korea","Department of Image, Chung-Ang University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Image,Seoul,Korea","institution_ids":["https://openalex.org/I67900169"]},{"raw_affiliation_string":"Department of Image, Chung-Ang University, Seoul, Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028893407"],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01507722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9969000220298767,"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":0.9891999959945679,"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":0.8355042934417725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6658499240875244},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.6547614932060242},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6228514313697815},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5614747405052185},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5161789059638977},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5065146684646606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8355042934417725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6658499240875244},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.6547614932060242},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6228514313697815},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5614747405052185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5161789059638977},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5065146684646606},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"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:10.1109/iceic57457.2023.10049847","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceic57457.2023.10049847","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334865","display_name":"Korea Customs Service","ror":"https://ror.org/01rkgg256"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2738406145","https://openalex.org/W2782422271","https://openalex.org/W2890952074","https://openalex.org/W2990452356","https://openalex.org/W2996833883","https://openalex.org/W3036601975","https://openalex.org/W4288088427","https://openalex.org/W6748181857","https://openalex.org/W6769148693","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2016546218","https://openalex.org/W1990932233","https://openalex.org/W2352223314","https://openalex.org/W2098980211","https://openalex.org/W166366606","https://openalex.org/W2509104183","https://openalex.org/W2509618504","https://openalex.org/W2156243485","https://openalex.org/W2014643887","https://openalex.org/W2162460942"],"abstract_inverted_index":{"Audio":[0],"driven":[1],"talking":[2,106],"face":[3,107],"methods":[4],"have":[5],"been":[6],"studied":[7],"to":[8,16,32,39,97,142],"process":[9],"the":[10,41,45,48,56,102,113,131,137],"accuracy":[11],"lip":[12,52,71,92],"synchronization.":[13],"However,":[14],"how":[15],"create":[17,47],"movement":[18],"of":[19],"head":[20,49,68,89],"poses":[21],"and":[22,51,54,70,86,91,145,149],"personalized":[23,57,99],"facial":[24,62],"features":[25,82,100],"is":[26,37,109,140],"a":[27,61,105,120],"challenging":[28],"problem.":[29],"In":[30,95,135],"order":[31,96],"solve":[33],"this":[34],"problem,":[35],"it":[36],"necessary":[38],"identify":[40],"context":[42],"based":[43],"on":[44,101],"audio,":[46],"pose":[50,69,90],"motion,":[53],"synthesize":[55,98],"face.":[58],"We":[59],"introduce":[60],"landmark":[63],"generation":[64],"method":[65,114,139],"including":[66],"audio-based":[67],"motion":[72,93],"using":[73],"an":[74],"audio":[75,78,81,132],"transformer.":[76],"The":[77],"transformer":[79],"extracts":[80],"containing":[83],"contextual":[84],"information":[85],"creates":[87],"generalized":[88],"landmarks.":[94],"generated":[103,110],"landmarks,":[104],"video":[108],"by":[111],"applying":[112],"learned":[115],"through":[116],"meta-learning.":[117],"With":[118],"just":[119],"few":[121],"single":[122],"images,":[123],"even":[124],"unknown":[125],"faces":[126],"can":[127],"be":[128],"spoken":[129],"in":[130],"you":[133],"want.":[134],"addition,":[136],"proposed":[138],"applicable":[141],"various":[143],"languages,":[144],"enables":[146],"photo-realistic":[147],"synthesis":[148],"fast":[150],"inference.":[151]},"counts_by_year":[],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}