{"id":"https://openalex.org/W4200342385","doi":"https://doi.org/10.1145/3490035.3490305","title":"Realistic talking face animation with speech-induced head motion","display_name":"Realistic talking face animation with speech-induced head motion","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4200342385","doi":"https://doi.org/10.1145/3490035.3490305"},"language":"en","primary_location":{"id":"doi:10.1145/3490035.3490305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490035.3490305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and Image Processing","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/A5056626512","display_name":"Sandika Biswas","orcid":"https://orcid.org/0000-0002-8264-3346"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sandika Biswas","raw_affiliation_strings":["TCS Research, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065928641","display_name":"Sanjana Sinha","orcid":"https://orcid.org/0000-0001-6198-1496"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sanjana Sinha","raw_affiliation_strings":["TCS Research, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021055773","display_name":"Dipanjan Das","orcid":"https://orcid.org/0000-0003-2325-0646"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dipanjan Das","raw_affiliation_strings":["TCS Research, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080835883","display_name":"Brojeshwar Bhowmick","orcid":"https://orcid.org/0000-0001-9291-5889"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Brojeshwar Bhowmick","raw_affiliation_strings":["TCS Research, India"],"affiliations":[{"raw_affiliation_string":"TCS Research, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056626512"],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":0.5764,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.69374183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9943000078201294,"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":0.9927999973297119,"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":0.8130984306335449},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.7720221281051636},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.6868422031402588},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6784382462501526},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6327378749847412},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5993170738220215},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.49915552139282227},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.4878418445587158},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.4816235899925232},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.4678992033004761},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.4226102828979492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41794413328170776},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40408438444137573},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2981805205345154},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.2050095796585083},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.196523517370224},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.15293502807617188},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.1242174506187439},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.10772696137428284},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.09813147783279419}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8130984306335449},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.7720221281051636},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.6868422031402588},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6784382462501526},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6327378749847412},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5993170738220215},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.49915552139282227},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.4878418445587158},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.4816235899925232},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.4678992033004761},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.4226102828979492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41794413328170776},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40408438444137573},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2981805205345154},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2050095796585083},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.196523517370224},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.15293502807617188},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.1242174506187439},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.10772696137428284},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.09813147783279419},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3490035.3490305","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490035.3490305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and Image Processing","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/W2029199293","https://openalex.org/W2096733369","https://openalex.org/W2118004237","https://openalex.org/W2124399597","https://openalex.org/W2133665775","https://openalex.org/W2146932984","https://openalex.org/W2162220380","https://openalex.org/W2187089797","https://openalex.org/W2325939864","https://openalex.org/W2331128040","https://openalex.org/W2603777577","https://openalex.org/W2738406145","https://openalex.org/W2807126412","https://openalex.org/W2944294033","https://openalex.org/W2963066677","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2969985801","https://openalex.org/W2979894294","https://openalex.org/W2990452356","https://openalex.org/W3019952993","https://openalex.org/W3081192838","https://openalex.org/W3081492798","https://openalex.org/W3089177030","https://openalex.org/W3089455867","https://openalex.org/W3101631197","https://openalex.org/W3109114891","https://openalex.org/W3186090335","https://openalex.org/W3197199219"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2748502319","https://openalex.org/W2401874398","https://openalex.org/W2295574089","https://openalex.org/W2906438086","https://openalex.org/W615219140","https://openalex.org/W2130702999","https://openalex.org/W2165663879","https://openalex.org/W4385825592","https://openalex.org/W2188148675"],"abstract_inverted_index":{"The":[0],"recent":[1,49],"advancements":[2],"on":[3,12,61],"talking":[4,101],"face":[5,102],"generation":[6],"from":[7],"speech":[8,84,148],"have":[9],"mostly":[10,59],"focused":[11],"lip":[13,111,173],"synchronization,":[14],"realistic":[15,100],"facial":[16],"movements":[17],"like":[18],"eye":[19,21],"blinks,":[20],"brow":[22],"motions":[23,30,108,195],"but":[24,57],"do":[25],"not":[26],"generate":[27],"meaningful":[28],"head":[29,55,65,73,107,136,152,171,194],"according":[31],"to":[32,52,127,179,201],"the":[33,54,70,79,83,129,134,140,143,147,150,197,202],"speech.":[34,45],"This":[35],"results":[36,155],"in":[37,43,163],"a":[38,62,86,95],"lack":[39],"of":[40,72,82,146,165,170],"realism,":[41],"especially":[42],"long":[44],"A":[46],"very":[47],"few":[48],"methods":[50],"try":[51],"animate":[53],"motions,":[56],"they":[58],"rely":[60],"short":[63],"driving":[64],"motion":[66,74,137],"video.":[67],"In":[68,90,119],"general,":[69],"prediction":[71],"is":[75],"largely":[76],"dependent":[77],"upon":[78],"prosodic":[80,144],"information":[81,145],"at":[85],"current":[87],"time":[88],"window.":[89],"this":[91],"paper,":[92],"we":[93,121],"propose":[94,122],"method":[96],"for":[97],"generating":[98],"speech-driven":[99],"animation":[103,198],"which":[104],"has":[105],"speech-coherent":[106,193],"with":[109,133],"accurate":[110],"sync,":[112,174],"natural":[113],"eye-blink,":[114],"and":[115,138,149,175,184],"high":[116],"fidelity":[117],"texture.":[118],"particular,":[120],"an":[123],"attention-based":[124],"GAN":[125],"network":[126],"identify":[128],"highly":[130],"correlated":[131],"audio":[132],"speaker's":[135],"learn":[139],"relationship":[141],"between":[142],"corresponding":[151],"motions.":[153],"Experimental":[154],"show":[156],"that":[157,191],"our":[158,187,192],"animations":[159],"are":[160],"significantly":[161],"better":[162],"terms":[164],"output":[166],"video":[167],"quality,":[168],"realism":[169],"movements,":[172],"eye-blinks":[176],"when":[177],"compared":[178],"state-of-the-art":[180],"methods,":[181],"both":[182],"qualitatively":[183],"quantitatively.":[185],"Moreover,":[186],"user":[188],"study":[189],"shows":[190],"make":[196],"more":[199],"appealing":[200],"users.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
