{"id":"https://openalex.org/W3096316132","doi":"https://doi.org/10.21437/interspeech.2020-1823","title":"Stochastic Talking Face Generation Using Latent Distribution Matching","display_name":"Stochastic Talking Face Generation Using Latent Distribution Matching","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096316132","doi":"https://doi.org/10.21437/interspeech.2020-1823","mag":"3096316132"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1823","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5010648323","display_name":"Ravindra Yadav","orcid":"https://orcid.org/0000-0003-4628-0688"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ravindra Yadav","raw_affiliation_strings":["Indian Institute of Technology Kanpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083439972","display_name":"Ashish Sardana","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ashish Sardana","raw_affiliation_strings":["nVidia"],"affiliations":[{"raw_affiliation_string":"nVidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007109424","display_name":"Vinay P. Namboodiri","orcid":"https://orcid.org/0000-0001-5262-9722"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinay P. Namboodiri","raw_affiliation_strings":["Indian Institute of Technology Kanpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085503354","display_name":"Rajesh M. Hegde","orcid":"https://orcid.org/0000-0002-6142-7724"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajesh M. Hegde","raw_affiliation_strings":["Indian Institute of Technology Kanpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Kanpur","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010648323"],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":0.3031,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55121791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1311","last_page":"1315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.998199999332428,"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":0.9955000281333923,"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":0.979200005531311,"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/autoencoder","display_name":"Autoencoder","score":0.8124417662620544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7944586277008057},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6090244650840759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5315601229667664},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5072655081748962},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49521008133888245},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.46873030066490173},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36768102645874023},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.1263570487499237},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08268293738365173}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8124417662620544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7944586277008057},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6090244650840759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5315601229667664},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5072655081748962},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49521008133888245},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.46873030066490173},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36768102645874023},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.1263570487499237},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08268293738365173},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1823","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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":0,"referenced_works":[],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2803255133"],"abstract_inverted_index":{"The":[0],"ability":[1,33,57,147],"to":[2,58,148],"envisage":[3],"the":[4,56,104,111,131,142,146],"visual":[5],"of":[6,26,44,103],"a":[7,14,17,24,42,60,66,85,120],"talking":[8,45,62],"face":[9,46,63],"based":[10,48],"just":[11,54],"on":[12,49,130],"hearing":[13],"voice":[15],"is":[16],"unique":[18],"human":[19],"capability.":[20],"There":[21],"have":[22,29],"been":[23],"number":[25],"works":[27],"that":[28,98,109],"solved":[30],"for":[31,81],"this":[32],"recently.":[34],"We":[35,107,116,126],"differ":[36],"from":[37,84],"these":[38],"approaches":[39],"by":[40],"enabling":[41],"variety":[43],"generations":[47,83,113],"single":[50,61,86],"audio":[51,87],"input.":[52,88],"Indeed,":[53],"having":[55,145],"generate":[59,149],"would":[64],"make":[65],"system":[67],"almost":[68],"robotic":[69],"in":[70],"nature.":[71],"In":[72],"contrast,":[73],"our":[74],"unsupervised":[75,93],"stochastic":[76,94],"audio-to-video":[77,95],"generation":[78,96],"model":[79,97],"allows":[80],"diverse":[82,112,151],"Particularly,":[89],"we":[90],"present":[91],"an":[92],"can":[99],"capture":[100],"multiple":[101,150],"modes":[102],"video":[105],"distribution.":[106],"ensure":[108],"all":[110],"are":[114],"plausible.":[115],"do":[117],"so":[118],"through":[119],"principled":[121],"multi-modal":[122],"variational":[123],"autoencoder":[124],"framework.":[125],"demonstrate":[127,138],"its":[128],"efficacy":[129],"challenging":[132],"LRW":[133],"and":[134,137],"GRID":[135],"datasets":[136],"performance":[139],"better":[140],"than":[141],"baseline,":[143],"while":[144],"lip":[152],"synchronized":[153],"videos.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}