{"id":"https://openalex.org/W4283818626","doi":"https://doi.org/10.1609/aaai.v36i2.20102","title":"SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory","display_name":"SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory","publication_year":2022,"publication_date":"2022-06-28","ids":{"openalex":"https://openalex.org/W4283818626","doi":"https://doi.org/10.1609/aaai.v36i2.20102"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v36i2.20102","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i2.20102","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20102/19861","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20102/19861","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100376688","display_name":"Se Jin Park","orcid":"https://orcid.org/0000-0001-8467-3576"},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["CA","KR"],"is_corresponding":true,"raw_author_name":"Se Jin Park","raw_affiliation_strings":["KAIST"],"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343629","display_name":"Minsu Kim","orcid":"https://orcid.org/0000-0002-6514-0018"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Minsu Kim","raw_affiliation_strings":["KAIST"],"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067120705","display_name":"Joanna Hong","orcid":"https://orcid.org/0000-0003-4182-1000"},"institutions":[{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]},{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Joanna Hong","raw_affiliation_strings":["KAIST"],"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101725649","display_name":"Jeongsoo Choi","orcid":"https://orcid.org/0009-0005-6817-604X"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Jeongsoo Choi","raw_affiliation_strings":["KAIST"],"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210099236","display_name":"Kootenay Association for Science & Technology","ror":"https://ror.org/011pv9p44","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210099236"]}],"countries":["CA","KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["KAIST"],"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I4210099236","https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100376688"],"corresponding_institution_ids":["https://openalex.org/I157485424","https://openalex.org/I4210099236"],"apc_list":null,"apc_paid":null,"fwci":9.1785,"has_fulltext":true,"cited_by_count":77,"citation_normalized_percentile":{"value":0.98677582,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"36","issue":"2","first_page":"2062","last_page":"2070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9954000115394592,"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":0.9954000115394592,"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/T11448","display_name":"Face recognition and analysis","score":0.9904999732971191,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.940500020980835,"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":0.8512060642242432},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5497310161590576},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5481633543968201},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5078118443489075},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4696599245071411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4466446340084076},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.43121621012687683},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4274991750717163},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42707911133766174},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4194050431251526},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.37661105394363403},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.13877564668655396},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.09506592154502869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8512060642242432},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5497310161590576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5481633543968201},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5078118443489075},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4696599245071411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4466446340084076},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.43121621012687683},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4274991750717163},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42707911133766174},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4194050431251526},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37661105394363403},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.13877564668655396},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.09506592154502869},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v36i2.20102","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i2.20102","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20102/19861","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v36i2.20102","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i2.20102","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/20102/19861","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5600000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283818626.pdf","grobid_xml":"https://content.openalex.org/works/W4283818626.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2115252128","https://openalex.org/W2604379605","https://openalex.org/W2798312258","https://openalex.org/W2798952503","https://openalex.org/W2883082281","https://openalex.org/W2890952074","https://openalex.org/W2914217321","https://openalex.org/W2944270022","https://openalex.org/W2944294033","https://openalex.org/W2950448185","https://openalex.org/W2950864153","https://openalex.org/W2953044442","https://openalex.org/W2962990649","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2963448850","https://openalex.org/W2963680240","https://openalex.org/W2964559396","https://openalex.org/W2979238975","https://openalex.org/W2979894294","https://openalex.org/W2981767644","https://openalex.org/W2995238198","https://openalex.org/W2999966482","https://openalex.org/W3006410788","https://openalex.org/W3007552021","https://openalex.org/W3010434693","https://openalex.org/W3015734344","https://openalex.org/W3025498998","https://openalex.org/W3025521275","https://openalex.org/W3034211329","https://openalex.org/W3081492798","https://openalex.org/W3089177030","https://openalex.org/W3097792222","https://openalex.org/W3105763085","https://openalex.org/W3109114891","https://openalex.org/W3110383967","https://openalex.org/W3142930505","https://openalex.org/W3155357996","https://openalex.org/W3180770160","https://openalex.org/W3181942264","https://openalex.org/W3186090335","https://openalex.org/W3197199219","https://openalex.org/W3202329597","https://openalex.org/W3203789665","https://openalex.org/W4287392530","https://openalex.org/W4303456115","https://openalex.org/W4320013936","https://openalex.org/W4411244923","https://openalex.org/W6677618333","https://openalex.org/W6734491695","https://openalex.org/W6735927292","https://openalex.org/W6750008037","https://openalex.org/W6754392867"],"related_works":["https://openalex.org/W2103413230","https://openalex.org/W1899364738","https://openalex.org/W43171467","https://openalex.org/W2908959303","https://openalex.org/W2663901905","https://openalex.org/W2138569648","https://openalex.org/W2143020626","https://openalex.org/W2126942212","https://openalex.org/W2116300362","https://openalex.org/W2018638282"],"abstract_inverted_index":{"The":[0],"challenge":[1],"of":[2,52,68,90],"talking":[3],"face":[4],"generation":[5],"from":[6,108],"speech":[7],"lies":[8],"in":[9,87,113,154,170,205],"aligning":[10],"two":[11],"different":[12],"modal":[13],"information,":[14],"audio":[15,97,122,131,150],"and":[16,42,98,117],"video,":[17],"such":[18,39],"that":[19,85,125,164,214,223],"the":[20,53,57,69,72,91,114,138,155,160,175,227],"mouth":[21,92,221],"region":[22,93],"corresponds":[23],"to":[24,48,95,212],"input":[25,96,132,228],"audio.":[26],"Previous":[27],"methods":[28],"either":[29],"exploit":[30],"audio-visual":[31,101,202],"representation":[32],"learning":[33],"or":[34],"leverage":[35],"intermediate":[36],"structural":[37],"information":[38,67,89],"as":[40,60,143],"landmarks":[41],"3D":[43],"models.":[44],"However,":[45],"they":[46,61,126],"struggle":[47],"synthesize":[49],"fine":[50],"details":[51],"lips":[54,70],"varying":[55],"at":[56,71,133,174],"phoneme":[58,176],"level":[59],"do":[62],"not":[63],"sufficiently":[64],"provide":[65],"visual":[66,88,144,152],"video":[73,219],"synthesis":[74,156],"step.":[75,157],"To":[76],"overcome":[77],"this":[78],"limitation,":[79],"our":[80,206,215],"work":[81],"proposes":[82],"Audio-Lip":[83],"Memory":[84],"brings":[86],"corresponding":[94,121],"enforces":[99],"fine-grained":[100],"coherence.":[102],"It":[103],"stores":[104],"lip":[105,140,166,180],"motion":[106,141,181],"features":[107,123,142,167],"sequential":[109],"ground":[110],"truth":[111],"images":[112],"value":[115],"memory":[116,172,184],"aligns":[118],"them":[119],"with":[120,151,201,220,226],"so":[124],"can":[127,147,194],"be":[128],"retrieved":[129,139],"using":[130,137],"inference":[134],"time.":[135],"Therefore,":[136],"hints,":[145],"it":[146],"easily":[148],"correlate":[149],"dynamics":[153],"By":[158],"analyzing":[159],"memory,":[161],"we":[162,188],"demonstrate":[163],"unique":[165],"are":[168,210],"stored":[169],"each":[171],"slot":[173],"level,":[177],"capturing":[178],"subtle":[179],"based":[182],"on":[183],"addressing.":[185],"In":[186],"addition,":[187],"introduce":[189],"visual-visual":[190],"synchronization":[191,203],"loss":[192,204],"which":[193],"enhance":[195],"lip-syncing":[196],"performance":[197],"when":[198],"used":[199],"along":[200],"model.":[207],"Extensive":[208],"experiments":[209],"performed":[211],"verify":[213],"method":[216],"generates":[217],"high-quality":[218],"shapes":[222],"best":[224],"align":[225],"audio,":[229],"outperforming":[230],"previous":[231],"state-of-the-art":[232],"methods.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}