{"id":"https://openalex.org/W2735090526","doi":"https://doi.org/10.1109/ijcnn.2017.7965918","title":"Audio visual speech recognition with multimodal recurrent neural networks","display_name":"Audio visual speech recognition with multimodal recurrent neural networks","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2735090526","doi":"https://doi.org/10.1109/ijcnn.2017.7965918","mag":"2735090526"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2017.7965918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7965918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","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/A5048113338","display_name":"Weijiang Feng","orcid":"https://orcid.org/0000-0002-5564-8977"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weijiang Feng","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, Hunan, P.R. China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, Hunan, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075453082","display_name":"Naiyang Guan","orcid":"https://orcid.org/0000-0002-6801-5714"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naiyang Guan","raw_affiliation_strings":["Science and Technology on Parallel, National University of Defense Technology, Changsha, Hunan, P.R. China"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel, National University of Defense Technology, Changsha, Hunan, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101841379","display_name":"Yuan Li","orcid":"https://orcid.org/0000-0001-9022-7345"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, Hunan, P.R. China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, Hunan, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368929","display_name":"Xiang Zhang","orcid":"https://orcid.org/0009-0001-9312-1762"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Zhang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, Hunan, P.R. China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, Hunan, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061811574","display_name":"Zhigang Luo","orcid":"https://orcid.org/0000-0002-7552-201X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhigang Luo","raw_affiliation_strings":["Science and Technology on Parallel, National University of Defense Technology, Changsha, Hunan, P.R. China"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel, National University of Defense Technology, Changsha, Hunan, P.R. China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048113338"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":5.7931,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.96970319,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"681","last_page":"688"},"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9940000176429749,"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":0.8120052814483643},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7354525923728943},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6928254961967468},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6215314865112305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6197340488433838},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5531439185142517},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5311455130577087},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5038384795188904},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.47543907165527344},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4509340524673462},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3382205665111542},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32991141080856323},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.07784119248390198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120052814483643},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7354525923728943},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6928254961967468},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6215314865112305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6197340488433838},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5531439185142517},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5311455130577087},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5038384795188904},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.47543907165527344},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4509340524673462},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3382205665111542},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32991141080856323},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.07784119248390198},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2017.7965918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7965918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W22517275","https://openalex.org/W1503933356","https://openalex.org/W1523385540","https://openalex.org/W1810943226","https://openalex.org/W1811254738","https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1993882792","https://openalex.org/W2015394094","https://openalex.org/W2022799064","https://openalex.org/W2064675550","https://openalex.org/W2076462394","https://openalex.org/W2079735306","https://openalex.org/W2096391593","https://openalex.org/W2107878631","https://openalex.org/W2113814270","https://openalex.org/W2122585011","https://openalex.org/W2130112859","https://openalex.org/W2130942839","https://openalex.org/W2131774270","https://openalex.org/W2136155248","https://openalex.org/W2143612262","https://openalex.org/W2157331557","https://openalex.org/W2167898728","https://openalex.org/W2171850596","https://openalex.org/W2183341477","https://openalex.org/W2184188583","https://openalex.org/W2194775991","https://openalex.org/W2271840356","https://openalex.org/W2404704342","https://openalex.org/W2474638510","https://openalex.org/W2962706528","https://openalex.org/W6631216910","https://openalex.org/W6679436768","https://openalex.org/W6684575925","https://openalex.org/W6686207219"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Studies":[0],"on":[1,192,216],"nowadays":[2],"human-machine":[3],"interface":[4],"have":[5],"demonstrated":[6],"that":[7],"visual":[8,29,54,70,97,111,121,130,157,213],"information":[9,55],"can":[10],"enhance":[11],"speech":[12,30,41,57],"recognition":[13,31,42,214],"accuracy":[14],"especially":[15],"in":[16,39,178],"noisy":[17],"environments.":[18],"Deep":[19],"learning":[20,49],"has":[21],"been":[22],"widely":[23],"used":[24],"to":[25,35,52,86,208],"tackle":[26],"such":[27],"audio":[28,68,95,109,118,128,147,212],"(AVSR)":[32],"problem":[33],"due":[34],"its":[36],"astonishing":[37],"achievements":[38],"both":[40,67,94,141,172],"and":[43,69,96,113,120,129,133,154,170,218],"image":[44],"recognition.":[45],"Although":[46],"existing":[47],"deep":[48],"models":[50,173],"succeed":[51],"incorporate":[53],"into":[56,88],"recognition,":[58],"none":[59],"of":[60,66,93,127,140,186,222],"them":[61],"simultaneously":[62],"considers":[63],"sequential":[64,91,125],"characteristics":[65,92,126],"modalities.":[71,142],"To":[72],"overcome":[73],"this":[74],"deficiency,":[75],"we":[76,144],"proposed":[77,188],"a":[78,151,161,167,175,193],"multimodal":[79,103,176,189,224],"recurrent":[80],"neural":[81,163],"network":[82,164],"(multimodal":[83],"RNN)":[84],"model":[85,191],"take":[87],"account":[89],"the":[90,117,124,134,138,146,156,179,184,187,204,209,220],"modalities":[98],"for":[99],"AVSR.":[100],"In":[101],"particular,":[102],"RNN":[104,190,225],"includes":[105],"three":[106],"components,":[107],"i.e.,":[108],"part,":[110,112,115],"fusion":[114,135,180],"where":[116],"part":[119,122,136],"capture":[123],"modalities,":[131],"respectively,":[132],"combines":[137],"outputs":[139],"Here":[143],"modelled":[145,155],"modality":[148,158],"by":[149,159,174],"using":[150,160],"LSTM":[152,168],"RNN,":[153,169],"convolutional":[162],"(CNN)":[165],"plus":[166],"combined":[171],"layer":[177],"part.":[181],"We":[182],"validated":[183],"effectiveness":[185],"multi-speaker":[194],"AVSR":[195],"benchmark":[196],"dataset":[197],"termed":[198],"AVletters.":[199],"The":[200],"experimental":[201],"results":[202],"show":[203],"performance":[205],"improvements":[206],"comparing":[207],"known":[210],"highest":[211],"accuracies":[215],"AVletters,":[217],"confirm":[219],"robustness":[221],"our":[223],"model.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":6}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}