{"id":"https://openalex.org/W4372346152","doi":"https://doi.org/10.1109/icassp49357.2023.10096889","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","display_name":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346152","doi":"https://doi.org/10.1109/icassp49357.2023.10096889"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":false,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":["Imperial College London,UK","Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010477883","display_name":"Alexandros Haliassos","orcid":"https://orcid.org/0000-0001-8856-5193"},"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":"Alexandros Haliassos","raw_affiliation_strings":["Imperial College London,UK","Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079540599","display_name":"Adriana Fernandez-Lopez","orcid":"https://orcid.org/0000-0001-8839-6537"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adriana Fernandez-Lopez","raw_affiliation_strings":["Meta AI,UK","Meta AI, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,UK","institution_ids":[]},{"raw_affiliation_string":"Meta AI, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081576515","display_name":"Honglie Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Honglie Chen","raw_affiliation_strings":["Meta AI,UK","Meta AI, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,UK","institution_ids":[]},{"raw_affiliation_string":"Meta AI, UK","institution_ids":[]}]},{"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,UK","Imperial College London, UK","Meta AI, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Meta AI, 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,UK","Imperial College London, UK","Meta AI, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Meta AI, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":28.7579,"has_fulltext":false,"cited_by_count":119,"citation_normalized_percentile":{"value":0.99859419,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9993000030517578,"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":0.9987000226974487,"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":0.8324553370475769},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7842217683792114},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7622787356376648},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6765927672386169},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.521828830242157},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5009753704071045},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.48066699504852295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47821447253227234},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4557376503944397},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4556882083415985},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42492133378982544},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41980335116386414},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36574864387512207},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14703267812728882},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.06356996297836304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324553370475769},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7842217683792114},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7622787356376648},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6765927672386169},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.521828830242157},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5009753704071045},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.48066699504852295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47821447253227234},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4557376503944397},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4556882083415985},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42492133378982544},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41980335116386414},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36574864387512207},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14703267812728882},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.06356996297836304},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1974387177","https://openalex.org/W2194775991","https://openalex.org/W2551572271","https://openalex.org/W2766219058","https://openalex.org/W2797583228","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2908510526","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963785710","https://openalex.org/W2963979492","https://openalex.org/W2974231335","https://openalex.org/W3006974783","https://openalex.org/W3015383493","https://openalex.org/W3015522062","https://openalex.org/W3015830103","https://openalex.org/W3026041220","https://openalex.org/W3030437843","https://openalex.org/W3035160371","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3101648800","https://openalex.org/W3139878283","https://openalex.org/W3162293946","https://openalex.org/W3162707322","https://openalex.org/W3167917117","https://openalex.org/W3197567540","https://openalex.org/W3209059054","https://openalex.org/W4221153068","https://openalex.org/W4221153521","https://openalex.org/W4289665794","https://openalex.org/W4297841641","https://openalex.org/W4297841719","https://openalex.org/W4307286264","https://openalex.org/W4312638101","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6750665317","https://openalex.org/W6754392867","https://openalex.org/W6754420807","https://openalex.org/W6757817989","https://openalex.org/W6767671539","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6785749098","https://openalex.org/W6810074610","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W2121652828","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W2186896963","https://openalex.org/W4372346152","https://openalex.org/W4361192867","https://openalex.org/W3143423642"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,24],"recognition":[2,25],"has":[3,31],"received":[4],"a":[5,132,163,170],"lot":[6],"of":[7,19,40,49,63,66,109,128,165,173],"attention":[8],"due":[9,36],"to":[10,37,69,84,139],"its":[11],"robustness":[12],"against":[13],"acoustic":[14],"noise.":[15],"Recently,":[16],"the":[17,38,61,71,103,110,118,126,129,136,177],"performance":[18,152],"automatic,":[20],"visual,":[21],"and":[22,28,43,53,92,99,112,157,181],"audio-visual":[23],"(ASR,":[26],"VSR,":[27],"AV-ASR,":[29],"respectively)":[30],"been":[32,186],"substantially":[33],"improved,":[34],"mainly":[35],"use":[39,62,79],"larger":[41],"models":[42,83,101],"training":[44,72,105,130,196],"sets.":[45],"However,":[46],"accurate":[47],"labelling":[48],"datasets":[50,68,88,114,191],"is":[51],"time-consuming":[52],"expensive.":[54],"Hence,":[55],"in":[56,135],"this":[57,76],"work,":[58],"we":[59,78,95],"investigate":[60],"automatically-generated":[64],"transcriptions":[65],"unlabelled":[67,87],"increase":[70],"set":[73],"size.":[74],"For":[75],"purpose,":[77],"publicly-available":[80],"pre-trained":[81],"ASR":[82],"automatically":[85],"transcribe":[86],"such":[89],"as":[90,115,117],"AVSpeech":[91],"Vox-Celeb2.":[93],"Then,":[94],"train":[96],"ASR,":[97],"VSR":[98],"AV-ASR":[100,154],"on":[102,153,155,168,188],"augmented":[104],"set,":[106,131],"which":[107],"consists":[108],"LRS2":[111,156],"LRS3":[113],"well":[116],"additional":[119],"automatically-transcribed":[120],"data.":[121,197],"We":[122],"demonstrate":[123],"that":[124,184],"increasing":[125],"size":[127],"recent":[133],"trend":[134],"literature,":[137],"leads":[138],"reduced":[140],"WER":[141,164],"despite":[142],"using":[143],"noisy":[144],"transcriptions.":[145],"The":[146],"proposed":[147],"model":[148],"achieves":[149,162],"new":[150],"state-of-the-art":[151],"LRS3.":[158],"In":[159],"particular,":[160],"it":[161],"0.9":[166],"%":[167,175],"LRS3,":[169],"relative":[171],"improvement":[172],"30":[174],"over":[176],"current":[178],"state-of-the\u2013art":[179],"approach,":[180],"outperforms":[182],"methods":[183],"have":[185],"trained":[187],"non-publicly":[189],"available":[190],"with":[192],"26":[193],"times":[194],"more":[195]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":59},{"year":2024,"cited_by_count":41},{"year":2023,"cited_by_count":10}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}