{"id":"https://openalex.org/W4387969537","doi":"https://doi.org/10.1145/3581783.3611787","title":"Towards Accurate Lip-to-Speech Synthesis in-the-Wild","display_name":"Towards Accurate Lip-to-Speech Synthesis in-the-Wild","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969537","doi":"https://doi.org/10.1145/3581783.3611787"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611787","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.01087","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/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":true,"raw_author_name":"Sindhu Hegde","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0005-2845-5570","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/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rudrabha Mukhopadhyay","raw_affiliation_strings":["IIIT Hyderabad, Hyderabad, India"],"raw_orcid":"https://orcid.org/0009-0000-6628-7065","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C.V Jawahar","raw_affiliation_strings":["IIIT Hyderabad, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0001-6767-7057","affiliations":[{"raw_affiliation_string":"IIIT Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","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 Namboodiri","raw_affiliation_strings":["University of Bath, Bath, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5262-9722","affiliations":[{"raw_affiliation_string":"University of Bath, Bath, United Kingdom","institution_ids":["https://openalex.org/I51601045"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081130373"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":1.727,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85800062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5523","last_page":"5531"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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":0.9968000054359436,"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":0.8335157632827759},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6303998827934265},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5940030813217163},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5850576162338257},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.4998185634613037},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4872354567050934},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4328327775001526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4130958318710327},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4118233323097229},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4113847315311432},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.1135396957397461},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10084861516952515}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8335157632827759},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6303998827934265},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5940030813217163},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5850576162338257},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.4998185634613037},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4872354567050934},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4328327775001526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4130958318710327},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4118233323097229},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4113847315311432},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.1135396957397461},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10084861516952515},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3611787","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2403.01087","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.01087","pdf_url":"https://arxiv.org/pdf/2403.01087","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.01087","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.01087","pdf_url":"https://arxiv.org/pdf/2403.01087","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332009","display_name":"International Institute of Information Technology, Hyderabad","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387969537.pdf","grobid_xml":"https://content.openalex.org/works/W4387969537.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2327501763","https://openalex.org/W2551437525","https://openalex.org/W2551572271","https://openalex.org/W2585824449","https://openalex.org/W2587741066","https://openalex.org/W2963019222","https://openalex.org/W2964243274","https://openalex.org/W3081492798","https://openalex.org/W3101631197","https://openalex.org/W3102516861","https://openalex.org/W3216976702","https://openalex.org/W4286696412","https://openalex.org/W4294435344","https://openalex.org/W4297841719","https://openalex.org/W4312638101","https://openalex.org/W4312916580"],"related_works":["https://openalex.org/W2063547430","https://openalex.org/W2524993630","https://openalex.org/W2607244263","https://openalex.org/W2234430299","https://openalex.org/W1831690014","https://openalex.org/W1561022130","https://openalex.org/W1995263003","https://openalex.org/W2222580448","https://openalex.org/W4206700937","https://openalex.org/W1971708112"],"abstract_inverted_index":{"In":[0],"this":[1,59],"paper,":[2],"we":[3,61,143],"introduce":[4],"a":[5,46,68,85,101],"novel":[6],"approach":[7,29,91],"to":[8,44,92,110],"address":[9],"the":[10,38,107,118,134,165],"task":[11],"of":[12,18,30,40,149],"synthesizing":[13],"speech":[14,33,51,157],"from":[15,34,50],"silent":[16,119],"videos":[17,36],"any":[19],"in-the-wild":[20],"speaker":[21],"solely":[22],"based":[23],"on":[24,138],"lip":[25,35],"movements.":[26,171],"The":[27,79],"traditional":[28],"directly":[31],"generating":[32,156],"faces":[37],"challenge":[39],"not":[41],"being":[42],"able":[43],"learn":[45],"robust":[47],"language":[48,74],"model":[49],"alone,":[52],"resulting":[53],"in":[54,152],"unsatisfactory":[55],"outcomes.":[56],"To":[57],"overcome":[58],"issue,":[60],"propose":[62],"incorporating":[63],"noisy":[64,80],"text":[65,81,95],"supervision":[66],"using":[67,84],"state-of-the-art":[69,136],"lip-to-text":[70,87],"network":[71,104],"that":[72,105],"instills":[73],"information":[75],"into":[76],"our":[77,90,130,150],"model.":[78],"is":[82,115],"generated":[83],"pre-trained":[86],"model,":[88],"enabling":[89],"work":[93],"without":[94],"annotations":[96],"during":[97],"inference.":[98],"We":[99,122],"design":[100],"visual":[102,108],"text-to-speech":[103],"utilizes":[106],"stream":[109],"generate":[111],"accurate":[112],"speech,":[113],"which":[114],"in-sync":[116],"with":[117],"input":[120],"video.":[121],"perform":[123],"extensive":[124],"experiments":[125],"and":[126,176],"ablation":[127],"studies,":[128],"demonstrating":[129],"approach's":[131],"superiority":[132],"over":[133],"current":[135],"methods":[137],"various":[139],"benchmark":[140],"datasets.":[141],"Further,":[142],"demonstrate":[144],"an":[145,159],"essential":[146],"practical":[147],"application":[148],"method":[151],"assistive":[153],"technology":[154],"by":[155],"for":[158],"ALS":[160],"patient":[161],"who":[162],"has":[163],"lost":[164],"voice":[166],"but":[167],"can":[168,179],"make":[169],"mouth":[170],"Our":[172],"demo":[173],"video,":[174],"code,":[175],"additional":[177],"details":[178],"be":[180],"found":[181],"at":[182],"http://cvit.iiit.ac.in/research/projects/cvit-projects/ms-l2s-itw.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}