{"id":"https://openalex.org/W4307286264","doi":"https://doi.org/10.1038/s42256-022-00550-z","title":"Visual speech recognition for multiple languages in the wild","display_name":"Visual speech recognition for multiple languages in the wild","publication_year":2022,"publication_date":"2022-10-24","ids":{"openalex":"https://openalex.org/W4307286264","doi":"https://doi.org/10.1038/s42256-022-00550-z"},"language":"en","primary_location":{"id":"doi:10.1038/s42256-022-00550-z","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-022-00550-z","pdf_url":null,"source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1038/s42256-022-00550-z","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001790767","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0003-3752-0803"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":["Imperial College London, London, UK"],"raw_orcid":"https://orcid.org/0000-0003-3752-0803","affiliations":[{"raw_affiliation_string":"Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Imperial College London, London, UK","Meta AI, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Meta AI, London, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Imperial College London, London, UK","Meta AI, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Meta AI, London, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001790767"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":{"value":11690,"currency":"USD","value_usd":11690},"apc_paid":{"value":11690,"currency":"USD","value_usd":11690},"fwci":15.7787,"has_fulltext":false,"cited_by_count":151,"citation_normalized_percentile":{"value":0.99726368,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"4","issue":"11","first_page":"930","last_page":"939"},"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":0.9994000196456909,"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":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8492188453674316},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.7703732252120972},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.6514286994934082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5567493438720703},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5423529744148254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5188597440719604},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45524993538856506},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4298974871635437},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4176548719406128},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34986457228660583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8492188453674316},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.7703732252120972},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.6514286994934082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5567493438720703},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5423529744148254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5188597440719604},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45524993538856506},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4298974871635437},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4176548719406128},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34986457228660583},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1038/s42256-022-00550-z","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-022-00550-z","pdf_url":null,"source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1038/s42256-022-00550-z","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s42256-022-00550-z","pdf_url":null,"source":{"id":"https://openalex.org/S2912241403","display_name":"Nature Machine Intelligence","issn_l":"2522-5839","issn":["2522-5839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nature Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W2008120082","https://openalex.org/W2014621385","https://openalex.org/W2015394094","https://openalex.org/W2093269413","https://openalex.org/W2096391593","https://openalex.org/W2121486117","https://openalex.org/W2151323546","https://openalex.org/W2230777371","https://openalex.org/W2341033924","https://openalex.org/W2551572271","https://openalex.org/W2890952074","https://openalex.org/W2891277050","https://openalex.org/W2902617128","https://openalex.org/W2905426022","https://openalex.org/W2936774411","https://openalex.org/W2949662773","https://openalex.org/W2962780374","https://openalex.org/W2962912639","https://openalex.org/W2962915147","https://openalex.org/W2963303028","https://openalex.org/W2963356069","https://openalex.org/W2963785710","https://openalex.org/W2964171275","https://openalex.org/W2972504708","https://openalex.org/W2973157397","https://openalex.org/W2996970093","https://openalex.org/W2999528291","https://openalex.org/W3006974783","https://openalex.org/W3015383493","https://openalex.org/W3015383801","https://openalex.org/W3015689952","https://openalex.org/W3015830103","https://openalex.org/W3034552680","https://openalex.org/W3035626590","https://openalex.org/W3038871978","https://openalex.org/W3080253586","https://openalex.org/W3097777922","https://openalex.org/W3100921325","https://openalex.org/W3104792420","https://openalex.org/W3139878283","https://openalex.org/W3144557079","https://openalex.org/W3157840621","https://openalex.org/W3161697668","https://openalex.org/W3162249256","https://openalex.org/W3162293946","https://openalex.org/W3162707322","https://openalex.org/W3167917117","https://openalex.org/W3175342695","https://openalex.org/W3197567540","https://openalex.org/W3197584784","https://openalex.org/W3197771105","https://openalex.org/W3199527474","https://openalex.org/W4289665794","https://openalex.org/W4297841719","https://openalex.org/W6753038255","https://openalex.org/W6969292531"],"related_works":["https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W2140186469","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W2775233965","https://openalex.org/W4318559728","https://openalex.org/W4360995913","https://openalex.org/W3094960827","https://openalex.org/W3000197790"],"abstract_inverted_index":{"Visual":[0],"speech":[1,10,169],"recognition":[2],"(VSR)":[3],"aims":[4],"to":[5,34,54,88,140,141,194],"recognize":[6],"the":[7,18,26,35,55,61,82,94,184],"content":[8],"of":[9,28,37,84,96,168,205],"based":[11],"on":[12,17,119,134,183],"lip":[13,171],"movements,":[14],"without":[15],"relying":[16],"audio":[19],"stream.":[20],"Advances":[21],"in":[22,155,164],"deep":[23],"learning":[24],"and":[25,41,92,99,113,178,213],"availability":[27],"large":[29,125],"audio-visual":[30],"datasets":[31,122,137],"have":[32,190],"led":[33],"development":[36],"much":[38,179],"more":[39,144],"accurate":[40],"robust":[42],"VSR":[43,90],"models":[44,70,130],"than":[45,60],"ever":[46],"before.":[47],"However,":[48],"these":[49],"advances":[50],"are":[51],"usually":[52],"due":[53],"larger":[56,77],"training":[57,78,152],"sets":[58],"rather":[59],"model":[62,108,197],"design.":[63],"Here":[64],"we":[65],"demonstrate":[66],"that":[67,105,131,149,199],"designing":[68],"better":[69],"is":[71,173,181],"equally":[72],"as":[73,75],"important":[74],"using":[76,150],"sets.":[79],"We":[80,103,146],"propose":[81],"addition":[83],"prediction-based":[85],"auxiliary":[86,192],"tasks":[87,193],"a":[89,107,124,175,196,203],"model,":[91],"highlight":[93],"importance":[95],"hyperparameter":[97],"optimization":[98],"appropriate":[100],"data":[101],"augmentations.":[102],"show":[104],"such":[106,198],"works":[109,201],"for":[110,202],"different":[111,206],"languages":[112,157],"outperforms":[114,129],"all":[115],"previous":[116],"methods":[117],"trained":[118,133],"publicly":[120],"available":[121,136],"by":[123],"margin.":[126],"It":[127],"even":[128,154],"were":[132],"non-publicly":[135],"containing":[138],"up":[139],"21":[142],"times":[143],"data.":[145],"show,":[147],"furthermore,":[148],"additional":[151],"data,":[153],"other":[156],"or":[158],"with":[159],"automatically":[160],"generated":[161],"transcriptions,":[162],"results":[163],"further":[165],"improvement.":[166],"Recognition":[167],"from":[170],"movements":[172],"still":[174],"challenging":[176],"problem":[177],"effort":[180],"concentrated":[182],"English":[185],"language.":[186],"Ma":[187],"et":[188],"al.":[189],"used":[191],"train":[195],"it":[200],"range":[204],"languages,":[207],"including":[208],"Mandarin,":[209],"Spanish,":[210],"Italian,":[211],"French":[212],"Portuguese.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":60},{"year":2024,"cited_by_count":47},{"year":2023,"cited_by_count":29}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}