{"id":"https://openalex.org/W3199527474","doi":"https://doi.org/10.1109/asru51503.2021.9688191","title":"Audio-Visual Speech Recognition is Worth $32\\times 32\\times 8$ Voxels","display_name":"Audio-Visual Speech Recognition is Worth $32\\times 32\\times 8$ Voxels","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3199527474","doi":"https://doi.org/10.1109/asru51503.2021.9688191","mag":"3199527474"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688191","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5023556869","display_name":"Dmitriy Serdyuk","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dmitriy Serdyuk","raw_affiliation_strings":["Google,New York,USA,10011"],"affiliations":[{"raw_affiliation_string":"Google,New York,USA,10011","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048852285","display_name":"Otavio Braga","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Otavio Braga","raw_affiliation_strings":["Google,New York,USA,10011"],"affiliations":[{"raw_affiliation_string":"Google,New York,USA,10011","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005881531","display_name":"Olivier Siohan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olivier Siohan","raw_affiliation_strings":["Google,New York,USA,10011"],"affiliations":[{"raw_affiliation_string":"Google,New York,USA,10011","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023556869"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":4.3022,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.98115747,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"796","last_page":"802"},"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":0.9987000226974487,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9941999912261963,"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":0.830621600151062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6569675803184509},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.622037410736084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.512092113494873},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3442270755767822},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34411147236824036},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09321948885917664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.830621600151062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6569675803184509},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.622037410736084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.512092113494873},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3442270755767822},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34411147236824036},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09321948885917664},{"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/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/asru51503.2021.9688191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688191","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1828163288","https://openalex.org/W1979651826","https://openalex.org/W2033256038","https://openalex.org/W2112796928","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2550980560","https://openalex.org/W2714726990","https://openalex.org/W2883429621","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2896457183","https://openalex.org/W2952746495","https://openalex.org/W2963155035","https://openalex.org/W2963925437","https://openalex.org/W2972756321","https://openalex.org/W3006974783","https://openalex.org/W3015830103","https://openalex.org/W3016010032","https://openalex.org/W3016176723","https://openalex.org/W3035042697","https://openalex.org/W3097777922","https://openalex.org/W3099202502","https://openalex.org/W3126721948","https://openalex.org/W3160681319","https://openalex.org/W3162293946","https://openalex.org/W3210279979","https://openalex.org/W4214612132","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638749077","https://openalex.org/W6645216118","https://openalex.org/W6679434410","https://openalex.org/W6729540071","https://openalex.org/W6739901393","https://openalex.org/W6746563140","https://openalex.org/W6752764193","https://openalex.org/W6754392867","https://openalex.org/W6755207826","https://openalex.org/W6765296696","https://openalex.org/W6770430305","https://openalex.org/W6790307280","https://openalex.org/W6793119350"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2166024367","https://openalex.org/W2772917594","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2079911747"],"abstract_inverted_index":{"Audio-visual":[0],"automatic":[1],"speech":[2,11],"recognition":[3,12],"(AV-ASR)":[4],"intro-duces":[5],"the":[6,10,21,24,30,42,68,95,121,140,156,166,173,181,187,190],"video":[7,31,102],"modality":[8],"into":[9],"process,":[13],"often":[14],"by":[15,20],"relying":[16],"on":[17,109,120,129,172],"information":[18],"conveyed":[19],"motion":[22],"of":[23,29,58,114,133,180,189],"speaker's":[25],"mouth.":[26],"The":[27],"use":[28],"signal":[32],"requires":[33],"extracting":[34],"visual":[35,81,98],"features,":[36],"which":[37],"are":[38],"then":[39],"combined":[40],"with":[41,55,100],"acoustic":[43],"features":[44,82],"to":[45,79,93,147],"build":[46],"an":[47,153],"AV-ASR":[48,154],"system":[49],"[1].":[50],"This":[51],"is":[52],"tra-ditionally":[53],"done":[54],"some":[56],"form":[57],"3D":[59,96],"convolutional":[60,97,150,167],"network":[61],"(e.g.":[62],"VGG)":[63],"as":[64,126,128,160,162],"widely":[65],"used":[66],"in":[67],"computer":[69],"vision":[70],"community.":[71],"Recently,":[72],"image":[73,85],"transformers":[74],"[2]":[75],"have":[76],"been":[77],"introduced":[78],"ex-tract":[80],"useful":[83],"for":[84,193],"classification":[86],"tasks.":[87],"In":[88],"this":[89],"work,":[90],"we":[91,184],"propose":[92],"replace":[94],"front-end":[99,142,158],"a":[101,110,130,137,148],"transformer":[103,157],"front-end.":[104],"We":[105],"train":[106],"our":[107,170],"systems":[108],"large-scale":[111],"dataset":[112],"composed":[113],"YouTube":[115,134],"videos":[116],"and":[117],"evaluate":[118],"performance":[119,145],"publicly":[122],"available":[123],"LRS3-TED":[124,174],"set,":[125],"well":[127,161],"large":[131],"set":[132,176],"videos.":[135],"On":[136,152],"lip-reading":[138],"task,":[139,155],"transformer-based":[141],"shows":[143],"superior":[144],"compared":[146],"strong":[149],"baseline.":[151,168],"performs":[159],"(or":[163],"better":[164],"than)":[165],"Fine-tuning":[169],"model":[171,192],"training":[175],"matches":[177],"previous":[178],"state":[179],"art.":[182],"Thus,":[183],"experimentally":[185],"show":[186],"viability":[188],"convolution-free":[191],"AV-ASR.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}