{"id":"https://openalex.org/W4297841411","doi":"https://doi.org/10.21437/interspeech.2022-11311","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","display_name":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841411","doi":"https://doi.org/10.21437/interspeech.2022-11311"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11311","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11311","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5101454455","display_name":"Joanna Hong","orcid":"https://orcid.org/0000-0001-9683-1260"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joanna Hong","raw_affiliation_strings":["KAIST, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343629","display_name":"Minsu Kim","orcid":"https://orcid.org/0000-0002-6514-0018"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsu Kim","raw_affiliation_strings":["KAIST, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089433636","display_name":"Daehun Yoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daehun Yoo","raw_affiliation_strings":["Genesis Lab Inc., Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genesis Lab Inc., Seoul, South Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["KAIST, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7839,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.93106704,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2838","last_page":"2842"},"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":0.9998000264167786,"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":0.9994999766349792,"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":0.787571132183075},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7828904390335083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6694133877754211},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5068057179450989},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46284765005111694},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.413601815700531},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4104297161102295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38149428367614746},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3564169108867645},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.2725103497505188},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26309341192245483},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.19989046454429626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787571132183075},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7828904390335083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6694133877754211},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5068057179450989},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46284765005111694},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.413601815700531},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4104297161102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38149428367614746},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3564169108867645},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2725103497505188},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26309341192245483},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.19989046454429626},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11311","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11311","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5178579001","display_name":null,"funder_award_id":"NRF-2022R1A2C2005529","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1494198834","https://openalex.org/W1503933356","https://openalex.org/W1522301498","https://openalex.org/W1974387177","https://openalex.org/W2076462394","https://openalex.org/W2147768505","https://openalex.org/W2194775991","https://openalex.org/W2526425061","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2952746495","https://openalex.org/W2963250244","https://openalex.org/W2963654155","https://openalex.org/W2963785710","https://openalex.org/W2981501041","https://openalex.org/W2996970093","https://openalex.org/W3006974783","https://openalex.org/W3015383493","https://openalex.org/W3035042697","https://openalex.org/W3097777922","https://openalex.org/W3121016465","https://openalex.org/W3123318516","https://openalex.org/W3162293946","https://openalex.org/W3205193540","https://openalex.org/W3209141406","https://openalex.org/W3211862173","https://openalex.org/W3213322812","https://openalex.org/W4221166189","https://openalex.org/W4224319127","https://openalex.org/W4303456115","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2539919382","https://openalex.org/W2547431347","https://openalex.org/W22517275","https://openalex.org/W2042419400","https://openalex.org/W2122924390","https://openalex.org/W2064347532","https://openalex.org/W2131711534","https://openalex.org/W2589081144","https://openalex.org/W2171620991","https://openalex.org/W189256204"],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3],"designing":[4],"a":[5,32,54],"noise-robust":[6],"end-to-end":[7,118],"Audio-Visual":[8],"Speech":[9],"Recognition":[10],"(AVSR)":[11],"system.To":[12],"this":[13],"end,":[14],"we":[15],"propose":[16],"Visual":[17],"Context-driven":[18],"Audio":[19],"Feature":[20],"Enhancement":[21],"module":[22],"(V-CAFE)":[23],"to":[24,41,52,103],"enhance":[25],"the":[26,43,60,66,83,98,116,121,126,132,147],"input":[27],"noisy":[28,77,138],"audio":[29,90,93],"speech":[30,113,139,143],"with":[31,82,97,120],"help":[33],"of":[34,45,108,128,131],"audio-visual":[35,150],"correspondence.The":[36],"proposed":[37,117,133],"V-CAFE":[38,122],"is":[39,135],"designed":[40],"capture":[42],"transition":[44],"lip":[46],"movements,":[47],"namely":[48],"visual":[49,62,99],"context":[50],"and":[51,101,110,141,153],"generate":[53],"noise":[55,84],"reduction":[56,85],"mask":[57,75,86],"by":[58],"considering":[59],"obtained":[61],"context.Through":[63],"context-dependent":[64],"modeling,":[65],"ambiguity":[67],"in":[68,88,137],"viseme-to-phoneme":[69],"mapping":[70],"can":[71,123],"be":[72],"refined":[73],"for":[74,112],"generation.The":[76],"representations":[78],"are":[79,95],"masked":[80],"out":[81],"resulting":[87],"enhanced":[89,92],"features.The":[91],"features":[94,100],"fused":[96],"taken":[102],"an":[104],"encoder-decoder":[105],"model":[106],"composed":[107],"Conformer":[109],"Transformer":[111],"recognition.We":[114],"show":[115],"AVSR":[119],"further":[124],"improve":[125],"noise-robustness":[127],"AVSR.The":[129],"effectiveness":[130],"method":[134],"evaluated":[136],"recognition":[140,144],"overlapped":[142],"experiments":[145],"using":[146],"two":[148],"largest":[149],"datasets,":[151],"LRS2":[152],"LRS3.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}