{"id":"https://openalex.org/W4223499953","doi":"https://doi.org/10.1109/tnnls.2022.3163771","title":"Multimodal Sparse Transformer Network for Audio-Visual Speech Recognition","display_name":"Multimodal Sparse Transformer Network for Audio-Visual Speech Recognition","publication_year":2022,"publication_date":"2022-04-12","ids":{"openalex":"https://openalex.org/W4223499953","doi":"https://doi.org/10.1109/tnnls.2022.3163771","pmid":"https://pubmed.ncbi.nlm.nih.gov/35412992"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3163771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3163771","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5018520101","display_name":"Qiya Song","orcid":"https://orcid.org/0000-0002-3115-0672"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiya Song","raw_affiliation_strings":["College of Electrical and Information Engineering and the Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-3115-0672","affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering and the Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641761","display_name":"Bin Sun","orcid":"https://orcid.org/0000-0002-7029-8784"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Sun","raw_affiliation_strings":["College of Electrical and Information Engineering and the Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-7029-8784","affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering and the Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067097659","display_name":"Shutao Li","orcid":"https://orcid.org/0000-0002-0585-9848"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shutao Li","raw_affiliation_strings":["College of Electrical and Information Engineering and the Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-0585-9848","affiliations":[{"raw_affiliation_string":"College of Electrical and Information Engineering and the Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":14.2814,"has_fulltext":false,"cited_by_count":119,"citation_normalized_percentile":{"value":0.99638894,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"34","issue":"12","first_page":"10028","last_page":"10038"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6579025387763977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6415484547615051},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.590627908706665},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5155258178710938},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.18249636888504028},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13274890184402466},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07972851395606995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6579025387763977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6415484547615051},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.590627908706665},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5155258178710938},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.18249636888504028},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13274890184402466},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07972851395606995},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2022.3163771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3163771","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35412992","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35412992","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.550000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7579875074","display_name":null,"funder_award_id":"62171183","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8651560819","display_name":null,"funder_award_id":"2018YFB1305200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W142803501","https://openalex.org/W1513100184","https://openalex.org/W1518556865","https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1563348166","https://openalex.org/W2015394094","https://openalex.org/W2021279213","https://openalex.org/W2096391593","https://openalex.org/W2140828385","https://openalex.org/W2296073425","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2806238143","https://openalex.org/W2889624961","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2901907199","https://openalex.org/W2931364255","https://openalex.org/W2941814890","https://openalex.org/W2947883281","https://openalex.org/W2962824709","https://openalex.org/W2963295405","https://openalex.org/W2963528589","https://openalex.org/W2963782415","https://openalex.org/W2963820951","https://openalex.org/W2964051877","https://openalex.org/W2964067226","https://openalex.org/W2964171275","https://openalex.org/W2970270554","https://openalex.org/W2986592617","https://openalex.org/W2997753998","https://openalex.org/W3012762803","https://openalex.org/W3015371109","https://openalex.org/W3016011581","https://openalex.org/W3034379322","https://openalex.org/W3035042697","https://openalex.org/W3097385349","https://openalex.org/W3102469722","https://openalex.org/W3127334095","https://openalex.org/W3127645834","https://openalex.org/W4298112588","https://openalex.org/W6605737493","https://openalex.org/W6631190155","https://openalex.org/W6679436768","https://openalex.org/W6682864246","https://openalex.org/W6732872814","https://openalex.org/W6739901393","https://openalex.org/W6754420807","https://openalex.org/W6761563299","https://openalex.org/W6763296340","https://openalex.org/W6767349417","https://openalex.org/W6772230799"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,43,59],"recognition":[2,44,60,201],"(ASR)":[3],"is":[4,111],"the":[5,29,55,67,75,81,108,115,119,133,154,163,169,176,190,221],"major":[6],"human-machine":[7],"interface":[8],"in":[9,28,63,94,132,145,218],"many":[10],"intelligent":[11,15],"systems,":[12],"such":[13],"as":[14,49],"homes,":[16],"autonomous":[17],"driving,":[18],"and":[19,77],"servant":[20],"robots.":[21],"However,":[22,88],"its":[23,38,89],"performance":[24,56,90],"usually":[25],"significantly":[26],"deteriorates":[27],"presence":[30],"of":[31,37,57,156,220],"external":[32],"noise,":[33],"leading":[34],"to":[35,53,73,98,122,184,194],"limitations":[36],"application":[39],"scenes.":[40],"The":[41,148],"audio-visual":[42],"(AVSR)":[45],"takes":[46],"visual":[47,125,187,196],"information":[48,101,117,160,183],"a":[50,85,139],"complementary":[51],"modality":[52,188],"enhance":[54,195],"audio":[58,76],"effectively,":[61],"particularly":[62],"noisy":[64],"conditions.":[65],"Recently,":[66],"transformer-based":[68],"architectures":[69,96],"have":[70],"been":[71,130],"used":[72],"model":[74],"video":[78],"sequences":[79,126],"for":[80,113],"AVSR,":[82],"which":[83],"achieves":[84],"superior":[86],"performance.":[87,202],"may":[91],"be":[92],"degraded":[93],"these":[95],"due":[97],"extracting":[99],"irrelevant":[100],"while":[102],"modeling":[103],"long-term":[104],"dependences.":[105],"In":[106],"addition,":[107],"motion":[109,170],"feature":[110],"essential":[112],"capturing":[114],"spatio-temporal":[116],"within":[118],"lip":[120],"region":[121],"best":[123],"utilize":[124],"but":[127],"has":[128],"not":[129],"considered":[131],"AVSR":[134],"tasks.":[135],"Therefore,":[136],"we":[137],"propose":[138],"multimodal":[140],"sparse":[141,149],"transformer":[142],"network":[143],"(MMST)":[144],"this":[146],"article.":[147],"self-attention":[150],"mechanism":[151],"can":[152],"improve":[153],"concentration":[155],"attention":[157,192],"on":[158,206],"global":[159],"by":[161],"selecting":[162],"most":[164],"relevant":[165],"parts":[166],"wisely.":[167],"Moreover,":[168],"features":[171],"are":[172],"seamlessly":[173],"introduced":[174],"into":[175,186],"MMST":[177],"model.":[178],"We":[179],"subtly":[180],"allow":[181],"motion-modality":[182],"flow":[185],"through":[189],"cross-modal":[191],"module":[193],"features,":[197],"thereby":[198],"further":[199],"improving":[200],"Extensive":[203],"experiments":[204],"conducted":[205],"different":[207],"datasets":[208],"validate":[209],"that":[210],"our":[211],"proposed":[212],"method":[213],"outperforms":[214],"several":[215],"state-of-the-art":[216],"methods":[217],"terms":[219],"word":[222],"error":[223],"rate":[224],"(WER).":[225]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":38},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}