{"id":"https://openalex.org/W3025521275","doi":"https://doi.org/10.1109/wacv45572.2020.9093527","title":"Animating Face using Disentangled Audio Representations","display_name":"Animating Face using Disentangled Audio Representations","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3025521275","doi":"https://doi.org/10.1109/wacv45572.2020.9093527","mag":"3025521275"},"language":"en","primary_location":{"id":"doi:10.1109/wacv45572.2020.9093527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","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/A5067385304","display_name":"Gaurav Mittal","orcid":"https://orcid.org/0000-0002-6942-3891"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Gaurav Mittal","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101902183","display_name":"Baoyuan Wang","orcid":"https://orcid.org/0000-0002-8268-7517"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Baoyuan Wang","raw_affiliation_strings":["Microsoft"],"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5067385304"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":4.8491,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.96089533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3279","last_page":"3287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987000226974487,"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":0.9986000061035156,"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":0.7699244618415833},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6398646235466003},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.614648163318634},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.5939149856567383},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5873427391052246},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5645484328269958},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4562394320964813},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.43960145115852356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3584166467189789},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.29257065057754517},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.18462634086608887},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0927291214466095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699244618415833},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6398646235466003},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.614648163318634},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.5939149856567383},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5873427391052246},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5645484328269958},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4562394320964813},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.43960145115852356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3584166467189789},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.29257065057754517},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.18462634086608887},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0927291214466095},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv45572.2020.9093527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv45572.2020.9093527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Winter Conference on Applications of Computer Vision (WACV)","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":51,"referenced_works":["https://openalex.org/W1569907127","https://openalex.org/W1901129140","https://openalex.org/W1922655562","https://openalex.org/W1959608418","https://openalex.org/W2015143272","https://openalex.org/W2030931454","https://openalex.org/W2063634999","https://openalex.org/W2468212864","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2758785877","https://openalex.org/W2769666294","https://openalex.org/W2782422271","https://openalex.org/W2790649793","https://openalex.org/W2797032258","https://openalex.org/W2797090057","https://openalex.org/W2804600264","https://openalex.org/W2804619907","https://openalex.org/W2891205112","https://openalex.org/W2949662773","https://openalex.org/W2962879692","https://openalex.org/W2963073614","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2963618559","https://openalex.org/W2964095416","https://openalex.org/W2964171275","https://openalex.org/W2981263323","https://openalex.org/W2984529706","https://openalex.org/W3104792420","https://openalex.org/W3123318516","https://openalex.org/W4295521014","https://openalex.org/W4320013936","https://openalex.org/W6639824700","https://openalex.org/W6640090968","https://openalex.org/W6640963894","https://openalex.org/W6734491695","https://openalex.org/W6735913928","https://openalex.org/W6735927292","https://openalex.org/W6737896281","https://openalex.org/W6745117592","https://openalex.org/W6748181857","https://openalex.org/W6749251296","https://openalex.org/W6750008037","https://openalex.org/W6750169759","https://openalex.org/W6751750676","https://openalex.org/W6754420807","https://openalex.org/W6770076868"],"related_works":["https://openalex.org/W1596769518","https://openalex.org/W2886693075","https://openalex.org/W3198503472","https://openalex.org/W4307784074","https://openalex.org/W3092864024","https://openalex.org/W3011644728","https://openalex.org/W2776235554","https://openalex.org/W2035430659","https://openalex.org/W2103937829","https://openalex.org/W2161829171"],"abstract_inverted_index":{"Previous":[0],"methods":[1],"for":[2,43,169],"audio-driven":[3],"talking":[4,48,157],"head":[5,49,158],"generation":[6,50,159],"assume":[7],"the":[8,35,92,110,142,149,154],"input":[9],"audio":[10,59,65,136,163],"to":[11,34,52,83,134],"be":[12],"clean":[13],"with":[14,125,139],"a":[15,161],"neutral":[16],"tone.":[17],"As":[18],"we":[19,55],"show":[20],"empirically,":[21],"one":[22],"can":[23],"easily":[24],"break":[25],"these":[26],"systems":[27],"by":[28,96,129],"simply":[29],"adding":[30],"certain":[31],"background":[32,76],"noise":[33,77,113],"utterance":[36],"or":[37],"changing":[38],"its":[39],"emotional":[40,74,115],"tone":[41],"(to":[42],"example,":[44],"sad).":[45],"To":[46,141],"make":[47],"robust":[51],"such":[53,70],"variations,":[54],"propose":[56],"an":[57],"explicit":[58],"representation":[60,138,164],"learning":[61],"framework":[62,122],"that":[63,85,120],"disentangles":[64],"sequences":[66],"into":[67],"various":[68],"factors":[69],"as":[71],"phonetic":[72],"content,":[73],"tone,":[75],"and":[78,114],"others.":[79],"We":[80,117],"conduct":[81],"experiments":[82],"validate":[84],"when":[86],"conditioned":[87],"on":[88],"disentangled":[89,107,162],"content":[90],"representation,":[91],"generated":[93],"mouth":[94],"movement":[95],"our":[97,121,145],"model":[98],"is":[99,123,148,167],"significantly":[100],"more":[101],"accurate":[102],"than":[103],"previous":[104],"approaches":[105,128],"(without":[106],"learning)":[108],"in":[109],"presence":[111],"of":[112,144,156],"variations.":[116],"further":[118],"demonstrate":[119],"compatible":[124],"current":[126],"state-of-the-art":[127],"replacing":[130],"their":[131],"original":[132],"component":[133],"learn":[135],"based":[137],"ours.":[140],"best":[143],"knowledge,":[146],"this":[147],"first":[150],"work":[151],"which":[152,166],"improves":[153],"performance":[155],"through":[160],"perspective,":[165],"important":[168],"many":[170],"real-world":[171],"applications.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}