{"id":"https://openalex.org/W4294435344","doi":"https://doi.org/10.1145/3503161.3548081","title":"Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild","display_name":"Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4294435344","doi":"https://doi.org/10.1145/3503161.3548081"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548081","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548081","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.00642","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081130373","display_name":"Sindhu B Hegde","orcid":"https://orcid.org/0009-0005-2845-5570"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sindhu B. Hegde","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031415279","display_name":"K R Prajwal","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"K R Prajwal","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007660270","display_name":"Rudrabha Mukhopadhyay","orcid":"https://orcid.org/0009-0000-6628-7065"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rudrabha Mukhopadhyay","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]},{"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/I51601045","display_name":"University of Bath","ror":"https://ror.org/002h8g185","country_code":"GB","type":"education","lineage":["https://openalex.org/I51601045"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vinay P. Namboodiri","raw_affiliation_strings":["University of Bath, Bath, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Bath, Bath, United Kingdom","institution_ids":["https://openalex.org/I51601045"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C.V. Jawahar","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081130373"],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":1.3363,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.83002833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6250","last_page":"6258"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9785000085830688,"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/speech-recognition","display_name":"Speech recognition","score":0.6307884454727173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6268634796142578},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6084768176078796},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34436166286468506}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6307884454727173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6268634796142578},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6084768176078796},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34436166286468506}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548081","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548081","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2209.00642","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.00642","pdf_url":"https://arxiv.org/pdf/2209.00642","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.00642","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.00642","pdf_url":"https://arxiv.org/pdf/2209.00642","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1924770834","https://openalex.org/W1959608418","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2193413348","https://openalex.org/W2331128040","https://openalex.org/W2551572271","https://openalex.org/W2585824449","https://openalex.org/W2604379605","https://openalex.org/W2624918875","https://openalex.org/W2730845691","https://openalex.org/W2738406145","https://openalex.org/W2739748921","https://openalex.org/W2782422271","https://openalex.org/W2808706139","https://openalex.org/W2887437849","https://openalex.org/W2890952074","https://openalex.org/W2914911817","https://openalex.org/W2950864153","https://openalex.org/W2952746495","https://openalex.org/W2963019222","https://openalex.org/W2963030892","https://openalex.org/W2963470893","https://openalex.org/W2963936489","https://openalex.org/W2964167449","https://openalex.org/W2964171275","https://openalex.org/W2964283370","https://openalex.org/W2964352155","https://openalex.org/W2972563022","https://openalex.org/W2982074157","https://openalex.org/W2996286887","https://openalex.org/W3005680577","https://openalex.org/W3014686072","https://openalex.org/W3016005719","https://openalex.org/W3035626590","https://openalex.org/W3081492798","https://openalex.org/W3101481642","https://openalex.org/W3101631197","https://openalex.org/W3105763085","https://openalex.org/W3116298410","https://openalex.org/W3201519611","https://openalex.org/W4289665794","https://openalex.org/W4295521014","https://openalex.org/W4297808394","https://openalex.org/W4298112588","https://openalex.org/W4301054805","https://openalex.org/W4312638101","https://openalex.org/W4402776467"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W127416991"],"abstract_inverted_index":{"In":[0,20,102],"this":[1],"work,":[2],"we":[3,109,163],"address":[4],"the":[5,18,45,48,59,75,83,98,119,125,128,136,150,204,225],"problem":[6],"of":[7,36,72,82,130,153,179,206,209],"generating":[8],"speech":[9,122,144],"from":[10,97],"silent":[11,99],"lip":[12,120,151],"videos":[13,54,178],"for":[14,149],"any":[15,147,154],"speaker":[16],"in":[17,58,146],"wild.":[19],"stark":[21],"contrast":[22],"to":[23,32,63,104,117,142,182,187,202],"previous":[24],"works,":[25],"our":[26,139,172,210,231],"method":[27],"(i)":[28],"is":[29],"not":[30,40],"restricted":[31],"a":[33,70,111,168,184,215],"fixed":[34],"number":[35],"speakers,":[37],"(ii)":[38],"does":[39],"explicitly":[41],"impose":[42],"constraints":[43],"on":[44,158,177,193,230],"domain":[46],"or":[47],"vocabulary":[49],"and":[50,90,121,227],"(iii)":[51],"deals":[52],"with":[53,74,224],"that":[55,79,115,134,162,190,218],"are":[56,191],"recorded":[57],"wild":[60],"as":[61],"opposed":[62],"within":[64],"laboratory":[65],"settings.":[66],"The":[67],"task":[68],"presents":[69],"host":[71],"challenges,":[73],"key":[76],"one":[77],"being":[78],"many":[80],"features":[81],"desired":[84],"target":[85],"speech,":[86],"like":[87],"voice,":[88],"pitch":[89],"linguistic":[91],"content,":[92],"cannot":[93],"be":[94,175],"entirely":[95],"inferred":[96],"face":[100],"video.":[101],"order":[103],"handle":[105],"these":[106],"stochastic":[107],"variations,":[108],"propose":[110],"new":[112],"VAE-GAN":[113],"architecture":[114],"learns":[116,141],"associate":[118],"sequences":[123,145],"amidst":[124],"variations.":[126],"With":[127],"help":[129],"multiple":[131,159],"powerful":[132],"discriminators":[133],"guide":[135],"training":[137],"process,":[138],"generator":[140],"synthesize":[143],"voice":[148],"movements":[152],"person.":[155],"Extensive":[156],"experiments":[157],"datasets":[160],"show":[161],"outperform":[164],"all":[165],"baselines":[166],"by":[167],"large":[169],"margin.":[170],"Further,":[171],"network":[173],"can":[174],"fine-tuned":[176],"specific":[180],"identities":[181],"achieve":[183],"performance":[185],"comparable":[186],"single-speaker":[188],"models":[189,229],"trained":[192,228],"$4\\times$":[194],"more":[195],"data.":[196],"We":[197,212],"conduct":[198],"numerous":[199],"ablation":[200],"studies":[201],"analyze":[203],"effect":[205],"different":[207],"modules":[208],"architecture.":[211],"also":[213],"provide":[214],"demo":[216],"video":[217],"demonstrates":[219],"several":[220],"qualitative":[221],"results":[222],"along":[223],"code":[226],"website":[232],"http://cvit.iiit.ac.in/research/projects/cvit-projects/lip-to-speech-synthesis.":[233]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}