{"id":"https://openalex.org/W4391331224","doi":"https://doi.org/10.1109/smc53992.2023.10394108","title":"An End-to-End Mandarin Audio-Visual Speech Recognition Model with a Feature Enhancement Module","display_name":"An End-to-End Mandarin Audio-Visual Speech Recognition Model with a Feature Enhancement Module","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4391331224","doi":"https://doi.org/10.1109/smc53992.2023.10394108"},"language":"en","primary_location":{"id":"doi:10.1109/smc53992.2023.10394108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53992.2023.10394108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5100376129","display_name":"Jinxin Wang","orcid":"https://orcid.org/0000-0003-4205-7673"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinxin Wang","raw_affiliation_strings":["Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China","Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I59028903"]},{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072105113","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0002-3763-5080"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["School of Computer Science, University of Technology Sydney,Sydney,Australia","School of Computer Science, University of Technology Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney,Sydney,Australia","institution_ids":["https://openalex.org/I114017466"]},{"raw_affiliation_string":"School of Computer Science, University of Technology Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100766490","display_name":"Zhongwen Guo","orcid":"https://orcid.org/0000-0002-6890-0107"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongwen Guo","raw_affiliation_strings":["Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China","Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I59028903"]},{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413473","display_name":"Xiaomei Li","orcid":"https://orcid.org/0000-0002-8870-3186"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomei Li","raw_affiliation_strings":["Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China","Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I59028903"]},{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658871","display_name":"Weigang Wang","orcid":"https://orcid.org/0000-0003-3623-1858"},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weigang Wang","raw_affiliation_strings":["Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China","Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Ocean University of China,Faculty of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I59028903"]},{"raw_affiliation_string":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China","institution_ids":["https://openalex.org/I59028903"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100376129"],"corresponding_institution_ids":["https://openalex.org/I59028903"],"apc_list":null,"apc_paid":null,"fwci":0.2042,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50015649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"572","last_page":"577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9657999873161316,"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":0.95169997215271,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8538975715637207},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8012736439704895},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7065589427947998},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5634220838546753},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5359865427017212},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5251283645629883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3434344232082367},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.12802425026893616},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09772846102714539}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8538975715637207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8012736439704895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7065589427947998},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5634220838546753},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5359865427017212},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5251283645629883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3434344232082367},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.12802425026893616},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09772846102714539},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc53992.2023.10394108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc53992.2023.10394108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2121486117","https://openalex.org/W2194775991","https://openalex.org/W2530876040","https://openalex.org/W2535388113","https://openalex.org/W2795024892","https://openalex.org/W2809734421","https://openalex.org/W2897492880","https://openalex.org/W2940262938","https://openalex.org/W2963192365","https://openalex.org/W2963402313","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2964042923","https://openalex.org/W2976712796","https://openalex.org/W2981938460","https://openalex.org/W2987026005","https://openalex.org/W2999528291","https://openalex.org/W3034399482","https://openalex.org/W3088364240","https://openalex.org/W3090571339","https://openalex.org/W3094892544","https://openalex.org/W3103322708","https://openalex.org/W3107497254","https://openalex.org/W3110440461","https://openalex.org/W3160348851","https://openalex.org/W3162293946","https://openalex.org/W3162596541","https://openalex.org/W3163107903","https://openalex.org/W3170697543","https://openalex.org/W3177052299","https://openalex.org/W4297841719","https://openalex.org/W6631190155","https://openalex.org/W6638444622","https://openalex.org/W6638667902","https://openalex.org/W6687566353","https://openalex.org/W6761630670","https://openalex.org/W6768872360","https://openalex.org/W6785851975"],"related_works":["https://openalex.org/W2374317326","https://openalex.org/W2990005675","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"Compared":[0],"to":[1,21,61,89],"relying":[2],"only":[3],"on":[4,120],"audio":[5,98],"information,":[6],"incorporating":[7],"visual":[8,95],"information":[9],"improves":[10],"speech":[11,40,115],"recognition":[12,41],"accuracy":[13],"in":[14],"noisy":[15],"environments.":[16],"Existing":[17],"works":[18],"are":[19],"prone":[20],"design":[22,50],"specific":[23],"architecture":[24],"for":[25,67,112],"feature":[26,29,70,91],"extraction,":[27],"neglecting":[28],"enhancement.":[30],"In":[31],"this":[32],"paper,":[33],"we":[34,49],"propose":[35],"an":[36],"end-to-end":[37],"Mandarin":[38,125],"audio-visual":[39,114],"model":[42],"with":[43],"a":[44,51],"Feature":[45,52,77,84],"Enhancement":[46,53,78,85],"Module.":[47],"Specifically,":[48],"Module":[54,79,86],"(FEM)":[55],"that":[56,134],"uses":[57],"deconvolution":[58],"and":[59,82,97,123,143],"up-sampling":[60],"obtain":[62],"the":[63,75,102,106,109,121,135,139,144,147],"twin":[64],"enhanced":[65],"data":[66,96],"generating":[68],"high-resolution":[69],"representation.":[71],"We":[72,100,117],"further":[73],"develop":[74],"Visual":[76],"(Visual":[80],"FEM)":[81,88],"Audio":[83],"(Audio":[87],"enhance":[90],"extraction":[92],"from":[93],"both":[94],"data.":[99],"incorporate":[101],"proposed":[103,136,151],"modules":[104],"into":[105],"blocks":[107],"of":[108,149],"Residual":[110],"Network":[111],"accurate":[113],"recognition.":[116],"conducted":[118],"experiments":[119],"CAS-VSR-W1k":[122],"Chinese":[124],"Lip":[126],"Reading":[127],"(CMLR)":[128],"datasets.":[129],"The":[130],"experimental":[131],"results":[132],"show":[133],"method":[137],"outperforms":[138],"selected":[140],"competitive":[141],"baselines":[142],"state-of-the-art,":[145],"indicating":[146],"superiority":[148],"our":[150],"modules.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}