{"id":"https://openalex.org/W3117993090","doi":"https://doi.org/10.23919/eusipco47968.2020.9287778","title":"Realistic Lip Animation from Speech for Unseen Subjects using Few-shot Cross-modal Learning","display_name":"Realistic Lip Animation from Speech for Unseen Subjects using Few-shot Cross-modal Learning","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3117993090","doi":"https://doi.org/10.23919/eusipco47968.2020.9287778","mag":"3117993090"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287778","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","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/A5054200773","display_name":"Swapna Agarwal","orcid":"https://orcid.org/0000-0002-2909-8342"},"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":"Swapna Agarwal","raw_affiliation_strings":["Research & Innovation, Tata Consultancy Services, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research & Innovation, Tata Consultancy Services, Kolkata, 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":["Research & Innovation, Tata Consultancy Services, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research & Innovation, Tata Consultancy Services, Kolkata, 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":["Research & Innovation, Tata Consultancy Services, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research & Innovation, Tata Consultancy Services, Kolkata, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55215948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"690","last_page":"694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976000189781189,"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":0.9905999898910522,"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":0.8888341188430786},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.6649509072303772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5644485354423523},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.546701967716217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44378119707107544},{"id":"https://openalex.org/keywords/computer-facial-animation","display_name":"Computer facial animation","score":0.4228753447532654},{"id":"https://openalex.org/keywords/computer-animation","display_name":"Computer animation","score":0.3046298325061798},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10328212380409241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8888341188430786},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.6649509072303772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5644485354423523},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.546701967716217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44378119707107544},{"id":"https://openalex.org/C138591656","wikidata":"https://www.wikidata.org/wiki/Q5157538","display_name":"Computer facial animation","level":4,"score":0.4228753447532654},{"id":"https://openalex.org/C69369342","wikidata":"https://www.wikidata.org/wiki/Q1401416","display_name":"Computer animation","level":3,"score":0.3046298325061798},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10328212380409241}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287778","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1922655562","https://openalex.org/W2015143272","https://openalex.org/W2137825550","https://openalex.org/W2331128040","https://openalex.org/W2604763608","https://openalex.org/W2738406145","https://openalex.org/W2753160622","https://openalex.org/W2914217321","https://openalex.org/W2945052639","https://openalex.org/W2962795401","https://openalex.org/W2963009026","https://openalex.org/W2963081548","https://openalex.org/W2963290645","https://openalex.org/W2963775850","https://openalex.org/W2979894294","https://openalex.org/W2981767644","https://openalex.org/W2990452356","https://openalex.org/W3105763085","https://openalex.org/W3127686677","https://openalex.org/W6640090968","https://openalex.org/W6702130928","https://openalex.org/W6717367658","https://openalex.org/W6736057607","https://openalex.org/W6737896281","https://openalex.org/W6743661861","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W1544039745","https://openalex.org/W2121378366","https://openalex.org/W2999276620","https://openalex.org/W2532377291","https://openalex.org/W1976926596","https://openalex.org/W2989004599","https://openalex.org/W3094080214","https://openalex.org/W2535923857","https://openalex.org/W2156310872","https://openalex.org/W2356609371"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,185],"Convolutional":[3],"Neural":[4],"Network":[5],"(CNN)":[6],"based":[7,49],"approaches":[8],"have":[9,147],"been":[10],"able":[11],"to":[12,142],"generate":[13],"convincing":[14],"talking":[15,20,56],"heads.":[16],"Personalization":[17],"of":[18,24,31,33,80,84,98,164,187],"such":[19,177],"heads":[21,57],"requires":[22],"training":[23],"the":[25,34,59,72,124,149,181],"model":[26,73,94,179],"with":[27,76,111],"a":[28,47,65,77,81,113,117],"large":[29,82],"number":[30],"examples":[32,115],"target":[35],"person.":[36],"This":[37],"is":[38,62,70,74,95],"also":[39],"time":[40,120,190],"consuming.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,139],"propose":[46],"meta-learning":[48],"few-shot":[50,114],"approach":[51],"for":[52,102,116],"generating":[53,99],"personalized":[54],"2D":[55],"where":[58],"lip":[60,144],"animation":[61,101],"driven":[63,129],"by":[64,130,176],"given":[66],"audio.":[67],"The":[68],"idea":[69],"that":[71,91,126,173],"meta-trained":[75,93],"dataset":[78],"consisting":[79],"variety":[83],"subjects'":[85],"ethnicity":[86],"and":[87,106,157,159,169,189],"vocabulary.":[88],"We":[89,146],"show":[90,172],"our":[92,160],"then":[96],"capable":[97],"realistic":[100],"previously":[103],"unseen":[104,107],"face":[105],"audio":[108,131],"when":[109],"finetuned":[110],"only":[112],"very":[118],"short":[119],"(180":[121],"seconds).":[122],"Considering":[123],"fact":[125],"facial":[127],"expressions":[128],"are":[132],"mainly":[133],"expressed":[134],"through":[135],"motion":[136],"around":[137],"lips,":[138],"restrict":[140],"ourselves":[141],"animating":[143],"only.":[145],"done":[148],"experiments":[150],"on":[151],"two":[152],"publicly":[153],"available":[154],"datasets:":[155],"GRID":[156],"TCD-TIMIT":[158],"own":[161],"captured":[162],"data":[163],"Asian":[165],"people.":[166],"Both":[167],"qualitative":[168],"quantitative":[170],"analysis":[171],"animations":[174],"generated":[175],"meta-learned":[178],"surpasses":[180],"state-of-the-art":[182],"methods":[183],"both":[184],"terms":[186],"realism":[188],"taken.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}