{"id":"https://openalex.org/W4372263374","doi":"https://doi.org/10.1109/icassp49357.2023.10095670","title":"DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions","display_name":"DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of Head Pose and Facial Expressions","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372263374","doi":"https://doi.org/10.1109/icassp49357.2023.10095670"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5070443803","display_name":"Geumbyeol Hwang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159322","display_name":"MemBrain (Czechia)","ror":"https://ror.org/05fmr5p93","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159322"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Geumbyeol Hwang","raw_affiliation_strings":["DeepBrain AI Inc.,Seoul,Korea","DeepBrain AI Inc., Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepBrain AI Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I4210159322"]},{"raw_affiliation_string":"DeepBrain AI Inc., Seoul, Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064510581","display_name":"Sunwon Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159322","display_name":"MemBrain (Czechia)","ror":"https://ror.org/05fmr5p93","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159322"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Sunwon Hong","raw_affiliation_strings":["DeepBrain AI Inc.,Seoul,Korea","DeepBrain AI Inc., Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepBrain AI Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I4210159322"]},{"raw_affiliation_string":"DeepBrain AI Inc., Seoul, Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426789","display_name":"Seunghyun Lee","orcid":"https://orcid.org/0000-0002-4701-2856"},"institutions":[{"id":"https://openalex.org/I4210159322","display_name":"MemBrain (Czechia)","ror":"https://ror.org/05fmr5p93","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159322"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Seunghyun Lee","raw_affiliation_strings":["DeepBrain AI Inc.,Seoul,Korea","DeepBrain AI Inc., Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepBrain AI Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I4210159322"]},{"raw_affiliation_string":"DeepBrain AI Inc., Seoul, Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324396","display_name":"Sungwoo Park","orcid":"https://orcid.org/0000-0001-5469-0332"},"institutions":[{"id":"https://openalex.org/I4210159322","display_name":"MemBrain (Czechia)","ror":"https://ror.org/05fmr5p93","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159322"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Sungwoo Park","raw_affiliation_strings":["DeepBrain AI Inc.,Seoul,Korea","DeepBrain AI Inc., Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepBrain AI Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I4210159322"]},{"raw_affiliation_string":"DeepBrain AI Inc., Seoul, Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008455163","display_name":"Gyeongsu Chae","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159322","display_name":"MemBrain (Czechia)","ror":"https://ror.org/05fmr5p93","country_code":"CZ","type":"company","lineage":["https://openalex.org/I4210159322"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Gyeongsu Chae","raw_affiliation_strings":["DeepBrain AI Inc.,Seoul,Korea","DeepBrain AI Inc., Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepBrain AI Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I4210159322"]},{"raw_affiliation_string":"DeepBrain AI Inc., Seoul, Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210159322"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9973999857902527,"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":0.9957000017166138,"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":0.8419986963272095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.600482165813446},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5544716119766235},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5485221147537231},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.49036574363708496},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4683277904987335},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4201469421386719},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4146685004234314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4057796001434326}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8419986963272095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.600482165813446},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5544716119766235},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5485221147537231},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.49036574363708496},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4683277904987335},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4201469421386719},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4146685004234314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4057796001434326},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2015143272","https://openalex.org/W2128409098","https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2738406145","https://openalex.org/W2950689937","https://openalex.org/W2963009026","https://openalex.org/W2964559396","https://openalex.org/W2979894294","https://openalex.org/W3008823916","https://openalex.org/W3015906192","https://openalex.org/W3019952993","https://openalex.org/W3035574324","https://openalex.org/W3081492798","https://openalex.org/W3087121792","https://openalex.org/W3096316132","https://openalex.org/W3097792222","https://openalex.org/W3101631197","https://openalex.org/W3107666850","https://openalex.org/W3109114891","https://openalex.org/W3178284600","https://openalex.org/W3186090335","https://openalex.org/W3187364420","https://openalex.org/W3197199219","https://openalex.org/W3202913169","https://openalex.org/W4312473638","https://openalex.org/W6637373629","https://openalex.org/W6765657114","https://openalex.org/W6767264202"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2765965840"],"abstract_inverted_index":{"For":[0],"realistic":[1,173],"talking":[2,175],"head":[3,7,31,51,124],"generation,":[4],"creating":[5],"natural":[6],"motion":[8,52,85,111,125],"while":[9],"maintaining":[10],"accurate":[11],"lip":[12],"synchronization":[13],"is":[14,112],"essential.":[15],"To":[16],"fulfill":[17],"this":[18],"challenging":[19],"task,":[20],"we":[21,102],"propose":[22,104],"DisCoHead,":[23],"a":[24,40,45,54,61,83,91,99,105,127,147],"novel":[25],"method":[26],"to":[27,47,126,136],"disentangle":[28],"and":[29,33,49,68,87,114,139,143,177],"control":[30],"pose":[32],"facial":[34],"expressions":[35],"without":[36],"supervision.":[37],"DisCoHead":[38,80,130,170],"uses":[39],"single":[41],"geometric":[42,73],"transformation":[43,64],"as":[44,72],"bottleneck":[46],"isolate":[48],"extract":[50],"from":[53],"head-driving":[55],"video.":[56],"Either":[57],"an":[58],"affine":[59],"or":[60],"thin-plate":[62],"spline":[63],"can":[65],"be":[66],"used":[67],"both":[69],"work":[70],"well":[71],"bottlenecks.":[74],"We":[75],"enhance":[76],"the":[77,88,118,122,132,152,156],"efficiency":[78],"of":[79,90,151,159],"by":[81,117],"integrating":[82],"dense":[84,110],"estimator":[86],"encoder":[89],"generator":[92],"which":[93],"are":[94],"originally":[95],"separate":[96,148],"modules.":[97],"Taking":[98],"step":[100],"further,":[101],"also":[103],"neural":[106,161],"mix":[107],"approach":[108],"where":[109],"estimated":[113],"applied":[115],"implicitly":[116],"encoder.":[119],"After":[120],"applying":[121],"disentangled":[123],"source":[128],"identity,":[129],"controls":[131],"mouth":[133],"region":[134],"according":[135],"speech":[137],"audio,":[138],"it":[140],"blinks":[141],"eyes":[142],"moves":[144],"eyebrows":[145],"following":[146],"driving":[149],"video":[150],"eye":[153],"region,":[154],"via":[155],"weight":[157],"modulation":[158],"convolutional":[160],"networks.":[162],"The":[163],"experiments":[164],"using":[165],"multiple":[166],"datasets":[167],"show":[168],"that":[169],"successfully":[171],"generates":[172],"audio-and-video-driven":[174],"heads":[176],"outperforms":[178],"state-of-the-art":[179],"methods.":[180],"Project":[181],"page:":[182],"https://deepbrainai-research.github.io/discohead/":[183]},"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":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}