{"id":"https://openalex.org/W4372267507","doi":"https://doi.org/10.1109/icassp49357.2023.10096893","title":"Robust Audio-Visual ASR with Unified Cross-Modal Attention","display_name":"Robust Audio-Visual ASR with Unified Cross-Modal Attention","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267507","doi":"https://doi.org/10.1109/icassp49357.2023.10096893"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096893","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":"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/A5100658801","display_name":"Jiahong Li","orcid":"https://orcid.org/0009-0002-0639-1519"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahong Li","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090224430","display_name":"Chenda Li","orcid":"https://orcid.org/0000-0003-0299-9914"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenda Li","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101452320","display_name":"Yifei Wu","orcid":"https://orcid.org/0009-0002-8201-6438"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100658801"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.4264,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81690141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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":0.9991999864578247,"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":0.9973000288009644,"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":0.8141961097717285},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6857988238334656},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6224008202552795},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.620387613773346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5490654706954956},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4867746829986572},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4296156167984009},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32902467250823975}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141961097717285},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6857988238334656},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6224008202552795},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.620387613773346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5490654706954956},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4867746829986572},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4296156167984009},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32902467250823975},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096893","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":[{"score":0.699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2076462394","https://openalex.org/W2194775991","https://openalex.org/W2289925289","https://openalex.org/W2512544816","https://openalex.org/W2551572271","https://openalex.org/W2808631503","https://openalex.org/W2889624961","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2901907199","https://openalex.org/W2936774411","https://openalex.org/W2943845043","https://openalex.org/W2963528589","https://openalex.org/W2963785710","https://openalex.org/W2972541922","https://openalex.org/W2972756321","https://openalex.org/W3011234510","https://openalex.org/W3015383493","https://openalex.org/W3015579786","https://openalex.org/W3047388929","https://openalex.org/W3097777922","https://openalex.org/W3102469722","https://openalex.org/W3106423890","https://openalex.org/W3162293946","https://openalex.org/W3196777808","https://openalex.org/W4221153068","https://openalex.org/W4221153521","https://openalex.org/W4297841641","https://openalex.org/W4308236834","https://openalex.org/W6631190155","https://openalex.org/W6734491695","https://openalex.org/W6734790163","https://openalex.org/W6754392867","https://openalex.org/W6754420807","https://openalex.org/W6781364056","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2380912101","https://openalex.org/W1984634519","https://openalex.org/W2801048620"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,16,68],"recognition":[2,17,69],"(AVSR)":[3],"takes":[4],"advantage":[5],"of":[6,14,46,49,142],"noise-invariant":[7],"visual":[8,32,81,144],"information":[9,51,124],"to":[10,120,135,138],"improve":[11],"the":[12,26,31,44,53,57,79,86,90,94,98,116,122,130,139,143,152,162,171],"robustness":[13],"automatic":[15],"(ASR)":[18],"systems.":[19],"While":[20],"previous":[21],"works":[22],"mainly":[23],"focused":[24],"on":[25],"clean":[27,166],"condition,":[28],"we":[29,63],"believe":[30],"modality":[33,145],"is":[34,83,133],"more":[35],"effective":[36],"in":[37,93,125,148],"noisy":[38,174],"environments.":[39],"The":[40],"challenges":[41],"arise":[42],"from":[43],"difficulty":[45],"adaptive":[47],"fusion":[48],"audio-visual":[50,67,123,149,154],"and":[52,109,168],"possible":[54],"interferences":[55],"inside":[56],"training":[58],"data.":[59],"In":[60,77,128],"this":[61],"paper,":[62],"present":[64],"a":[65,72,105],"new":[66,158],"model":[70,117,132,159],"with":[71,85],"unified":[73,95],"cross-modal":[74,107],"attention":[75],"mechanism.":[76],"particular,":[78],"auxiliary":[80],"evidence":[82],"combined":[84],"acoustic":[87],"feature":[88],"along":[89],"temporal":[91],"dimension":[92],"space":[96],"before":[97],"deep":[99],"encoding":[100],"network.":[101],"This":[102],"method":[103],"provides":[104],"flexible":[106],"context":[108],"requires":[110],"no":[111],"forced":[112],"alignment":[113],"such":[114],"that":[115],"can":[118],"learn":[119],"leverage":[121],"relevant":[126],"frames.":[127,150],"experiments,":[129],"proposed":[131],"demonstrated":[134],"be":[136],"robust":[137],"potential":[140],"absence":[141],"or":[146],"misalignment":[147],"On":[151],"large-scale":[153],"dataset":[155],"LRS3,":[156],"our":[157],"further":[160],"reduces":[161],"state-of-the-art":[163],"WER":[164],"for":[165],"utterances":[167],"significantly":[169],"improves":[170],"performance":[172],"under":[173],"conditions.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}