{"id":"https://openalex.org/W3163456394","doi":"https://doi.org/10.1109/icpr48806.2021.9412349","title":"Mutual Alignment between Audiovisual Features for End-to-End Audiovisual Speech Recognition","display_name":"Mutual Alignment between Audiovisual Features for End-to-End Audiovisual Speech Recognition","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3163456394","doi":"https://doi.org/10.1109/icpr48806.2021.9412349","mag":"3163456394"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5100410326","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0002-7498-6541"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Key Laboratory of Machine Perception Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434922","display_name":"Yawei Wang","orcid":"https://orcid.org/0000-0001-7760-1494"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yawei Wang","raw_affiliation_strings":["Key Laboratory of Machine Perception Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086513946","display_name":"Bing Yang","orcid":"https://orcid.org/0000-0002-8978-2322"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Yang","raw_affiliation_strings":["Key Laboratory of Machine Perception Shenzhen Graduate School, Peking University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception Shenzhen Graduate School, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5348","last_page":"5353"},"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":0.9990000128746033,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7726452946662903},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7356464862823486},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.6643729209899902},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5244446396827698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5168026685714722},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5158290266990662},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4522165060043335},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4455997347831726},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4194723963737488},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12205153703689575}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726452946662903},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7356464862823486},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6643729209899902},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5244446396827698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5168026685714722},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5158290266990662},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4522165060043335},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4455997347831726},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4194723963737488},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12205153703689575},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1512799051","display_name":null,"funder_award_id":"JCYJ20190808182209321","funder_id":"https://openalex.org/F4320325571","funder_display_name":"Shenzhen University"},{"id":"https://openalex.org/G401644923","display_name":null,"funder_award_id":"61673030,U1613209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320325571","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W101129729","https://openalex.org/W1522301498","https://openalex.org/W1974387177","https://openalex.org/W2015394094","https://openalex.org/W2048198238","https://openalex.org/W2071932093","https://openalex.org/W2095705004","https://openalex.org/W2116258879","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2155765376","https://openalex.org/W2157190406","https://openalex.org/W2164450870","https://openalex.org/W2194775991","https://openalex.org/W2594690981","https://openalex.org/W2889624961","https://openalex.org/W2897067191","https://openalex.org/W2901907199","https://openalex.org/W2962824709","https://openalex.org/W2963403868","https://openalex.org/W2963654155","https://openalex.org/W2964121744","https://openalex.org/W2971183306","https://openalex.org/W2984814708","https://openalex.org/W3102469722","https://openalex.org/W4244018879","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6674330103","https://openalex.org/W6684209796","https://openalex.org/W6734491695","https://openalex.org/W6739901393","https://openalex.org/W6767988601"],"related_works":["https://openalex.org/W2938286185","https://openalex.org/W2951125461","https://openalex.org/W2005071453","https://openalex.org/W2546942002","https://openalex.org/W2970216048","https://openalex.org/W2382607599","https://openalex.org/W1966366482","https://openalex.org/W2789928768","https://openalex.org/W4303038597","https://openalex.org/W3206503703"],"abstract_inverted_index":{"Asynchronization":[0],"issue":[1,123],"caused":[2],"by":[3,124,142],"different":[4],"types":[5],"of":[6,10,30,35,70,115,159],"modalities":[7],"is":[8,206],"one":[9],"the":[11,45,55,68,71,78,81,121,148,155,175,181,194],"major":[12],"problems":[13],"in":[14,138],"audio":[15,36,39,149,176],"visual":[16,41,151],"speech":[17,88],"recognition":[18,186],"(AVSR)":[19],"research.":[20],"However,":[21],"most":[22],"AVSR":[23,109],"systems":[24,76],"merely":[25],"rely":[26],"on":[27,154],"up":[28,171],"sampling":[29,34],"video":[31,90],"or":[32],"down":[33],"to":[37,86,119,172,219],"align":[38,87],"and":[40,61,66,89,150,202],"features,":[42,152],"assuming":[43],"that":[44,164,208],"feature":[46,105,196,212],"sequences":[47],"are":[48,75],"aligned":[49],"frame-by-frame.":[50],"These":[51],"pre-processing":[52],"steps":[53],"oversimplify":[54],"asynchrony":[56,79],"relation":[57],"between":[58,80,147],"acoustic":[59],"signal":[60],"lip":[62],"motion,":[63],"lacking":[64],"flexibility":[65],"impairing":[67],"performance":[69,187],"system.":[72],"Although":[73],"there":[74],"modeling":[77],"modalities,":[82],"sometimes":[83],"they":[84],"fail":[85],"precisely":[91],"over":[92,174],"some":[93],"even":[94],"all":[95],"noisy":[96,203],"conditions.":[97,204],"In":[98],"this":[99],"paper,":[100],"we":[101],"propose":[102],"a":[103,139],"mutual":[104,140,144,211],"alignment":[106,137,213],"method":[107,132,167,198,214],"for":[108],"which":[110],"can":[111,133,188,215],"make":[112],"full":[113],"use":[114],"cross":[116],"modility":[117],"information":[118],"address":[120],"asynchronization":[122],"introducing":[125],"Mutual":[126],"Iterative":[127],"Attention":[128],"(MIA)":[129],"mechanism.":[130],"Our":[131],"automatically":[134],"learn":[135],"an":[136],"way":[141],"performing":[143],"attention":[145],"iteratively":[146],"relying":[153],"modified":[156],"encoder":[157],"structure":[158],"Transformer.":[160],"Experimental":[161],"results":[162],"show":[163],"our":[165,209],"proposed":[166,210],"obtains":[168],"absolute":[169],"improvements":[170],"20.42%":[173],"modality":[177],"alone":[178],"depending":[179],"upon":[180],"signal-to-noise-ratio":[182],"(SNR)":[183],"level.":[184],"Better":[185],"also":[189],"be":[190,216],"achieved":[191],"comparing":[192],"with":[193,223],"traditional":[195],"concatenation":[197],"under":[199],"both":[200],"clean":[201],"It":[205],"expectable":[207],"easily":[217],"generalized":[218],"other":[220],"multimodal":[221],"tasks":[222],"semantically":[224],"correlated":[225],"information.":[226]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}