{"id":"https://openalex.org/W3162293946","doi":"https://doi.org/10.1109/icassp39728.2021.9414567","title":"End-To-End Audio-Visual Speech Recognition with Conformers","display_name":"End-To-End Audio-Visual Speech Recognition with Conformers","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162293946","doi":"https://doi.org/10.1109/icassp39728.2021.9414567","mag":"3162293946"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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,Department of Computing,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,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,Department of Computing,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]}]},{"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,Department of Computing,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Computing,UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":29.9133,"has_fulltext":false,"cited_by_count":220,"citation_normalized_percentile":{"value":0.99903368,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7613","last_page":"7617"},"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":0.9976999759674072,"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":0.9944999814033508,"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":0.8177013397216797},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6714661121368408},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6339327096939087},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6096296906471252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5580626130104065},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5146778225898743},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4705249071121216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37262648344039917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3226618766784668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8177013397216797},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6714661121368408},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6339327096939087},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6096296906471252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5580626130104065},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5146778225898743},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4705249071121216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37262648344039917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3226618766784668},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414567","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1974387177","https://openalex.org/W2015143272","https://openalex.org/W2096391593","https://openalex.org/W2115252128","https://openalex.org/W2121486117","https://openalex.org/W2194775991","https://openalex.org/W2551572271","https://openalex.org/W2567070169","https://openalex.org/W2578229578","https://openalex.org/W2766219058","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2936774411","https://openalex.org/W2943845043","https://openalex.org/W2952746495","https://openalex.org/W2963071736","https://openalex.org/W2963403868","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2963785710","https://openalex.org/W2963970792","https://openalex.org/W2964110616","https://openalex.org/W2964121744","https://openalex.org/W2972504708","https://openalex.org/W2972756321","https://openalex.org/W2981501041","https://openalex.org/W2996970093","https://openalex.org/W3006974783","https://openalex.org/W3011234510","https://openalex.org/W3015383493","https://openalex.org/W3015579786","https://openalex.org/W3015830103","https://openalex.org/W3016011581","https://openalex.org/W3035042697","https://openalex.org/W3097450720","https://openalex.org/W3097777922","https://openalex.org/W3106423890","https://openalex.org/W3144810982","https://openalex.org/W3162707322","https://openalex.org/W4298112588","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6677618333","https://openalex.org/W6731370813","https://openalex.org/W6732872814","https://openalex.org/W6739901393","https://openalex.org/W6754392867","https://openalex.org/W6754420807","https://openalex.org/W6780483730","https://openalex.org/W6781171973"],"related_works":["https://openalex.org/W159132833","https://openalex.org/W4385877744","https://openalex.org/W2936858556","https://openalex.org/W4385873483","https://openalex.org/W4311156851","https://openalex.org/W4318978824","https://openalex.org/W4312784228","https://openalex.org/W3210438479","https://openalex.org/W2892009249","https://openalex.org/W3163605596"],"abstract_inverted_index":{"In":[0,25],"this":[1],"work,":[2],"we":[3],"present":[4,118],"a":[5,11,56,67,95,99,106,154],"hybrid":[6],"CTC/Attention":[7],"model":[8,61],"based":[9],"on":[10,120],"ResNet-18":[12],"and":[13,29,40,50,71,102,135,160],"Convolution-augmented":[14],"transformer":[15],"(Conformer),":[16],"that":[17,77,145],"can":[18],"be":[19],"trained":[20],"in":[21,89,157],"an":[22,72],"end-to-end":[23,78],"manner.":[24],"particular,":[26],"the":[27,90,92,103,112,121,150],"audio":[28,41],"visual":[30,84],"encoders":[31],"learn":[32],"to":[33,48,63],"extract":[34],"features":[35,85],"directly":[36],"from":[37],"raw":[38],"pixels":[39],"waveforms,":[42],"respectively,":[43],"which":[44,86],"are":[45],"then":[46,51],"fed":[47],"conformers":[49],"fusion":[52],"takes":[53],"place":[54],"via":[55],"Multi-Layer":[57],"Perceptron":[58],"(MLP).":[59],"The":[60,142],"learns":[62],"recognise":[64],"characters":[65],"using":[66,82],"combination":[68],"of":[69,81,94,98,105,114],"CTC":[70],"attention":[73],"mechanism.":[74],"We":[75,117],"show":[76,144],"training,":[79],"instead":[80,97],"pre-computed":[83],"is":[87],"common":[88],"literature,":[91],"use":[93,104],"conformer,":[96],"recurrent":[100],"network,":[101],"transformer-based":[107],"language":[108],"model,":[109],"significantly":[110],"improve":[111],"performance":[113,152],"our":[115,146],"model.":[116],"results":[119,143],"largest":[122],"publicly":[123],"available":[124],"datasets":[125],"for":[126],"sentence-level":[127],"speech":[128],"recognition,":[129],"Lip":[130,136],"Reading":[131,137],"Sentences":[132,138],"2":[133],"(LRS2)":[134],"3":[139],"(LRS3),":[140],"respectively.":[141],"proposed":[147],"models":[148],"raise":[149],"state-of-the-art":[151],"by":[153],"large":[155],"margin":[156],"audio-only,":[158],"visual-only,":[159],"audio-visual":[161],"experiments.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":69},{"year":2023,"cited_by_count":56},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":8}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}