{"id":"https://openalex.org/W4389151449","doi":"https://doi.org/10.1007/s00521-023-08959-2","title":"Intelligent speech recognition algorithm in multimedia visual interaction via BiLSTM and attention mechanism","display_name":"Intelligent speech recognition algorithm in multimedia visual interaction via BiLSTM and attention mechanism","publication_year":2023,"publication_date":"2023-11-29","ids":{"openalex":"https://openalex.org/W4389151449","doi":"https://doi.org/10.1007/s00521-023-08959-2"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-023-08959-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-08959-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-08959-2.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-08959-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108427335","display_name":"Yican Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yican Feng","raw_affiliation_strings":["Advanced Film School, Chung-Ang University, Seoul, 156756, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Film School, Chung-Ang University, Seoul, 156756, Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108427335"],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":1.1643,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78009148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"36","issue":"5","first_page":"2371","last_page":"2383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"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":0.9966999888420105,"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":0.993399977684021,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8348017930984497},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6949542760848999},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6412159204483032},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5624253153800964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4588935375213623},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45169445872306824},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4424203038215637},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4402911067008972},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4163523316383362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348017930984497},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6949542760848999},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6412159204483032},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5624253153800964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4588935375213623},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45169445872306824},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4424203038215637},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4402911067008972},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4163523316383362},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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:10.1007/s00521-023-08959-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-08959-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-08959-2.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-023-08959-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-023-08959-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-023-08959-2.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16"},{"display_name":"Reduced inequalities","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389151449.pdf","grobid_xml":"https://content.openalex.org/works/W4389151449.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1920923476","https://openalex.org/W2067474491","https://openalex.org/W2078204800","https://openalex.org/W2117671523","https://openalex.org/W2144499799","https://openalex.org/W2157331557","https://openalex.org/W2327501763","https://openalex.org/W2910692330","https://openalex.org/W2923984502","https://openalex.org/W2962778134","https://openalex.org/W2962826786","https://openalex.org/W2963308316","https://openalex.org/W3092058276","https://openalex.org/W3116293616","https://openalex.org/W3119859200","https://openalex.org/W3132830522","https://openalex.org/W3195642667","https://openalex.org/W3198752054","https://openalex.org/W4200174001","https://openalex.org/W4210930959","https://openalex.org/W4213425389","https://openalex.org/W4221094122","https://openalex.org/W4226023758","https://openalex.org/W4283121045","https://openalex.org/W4283319182","https://openalex.org/W4285728360","https://openalex.org/W4297841651","https://openalex.org/W4319302797","https://openalex.org/W4385508690"],"related_works":["https://openalex.org/W1834994814","https://openalex.org/W2981428355","https://openalex.org/W1599055764","https://openalex.org/W2041273198","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2131711534","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Abstract":[0],"With":[1],"the":[2,11,30,52,58,78,82,90,94,103,129,165,177,185,195,201,222,229,234,239,250,254,257],"rapid":[3],"development":[4],"of":[5,13,32,38,46,49,55,75,77,124,146,181,189,231],"information":[6,106,153,217],"technology":[7],"in":[8,29,119],"modern":[9],"society,":[10],"application":[12],"multimedia":[14,33,120],"integration":[15],"platform":[16],"is":[17,41,64,198],"more":[18,20,215],"and":[19,57,66,168,184,204,237,253],"extensive.":[21],"Speech":[22,62],"recognition":[23,40,60,97,118],"has":[24,244],"become":[25],"an":[26],"important":[27],"subject":[28],"process":[31],"visual":[34,121],"interaction.":[35,122],"The":[36,210],"accuracy":[37],"speech":[39,56,59,83,96,105,117,139,152,216],"dependent":[42],"on":[43,164,176,233,249],"a":[44,72,113,132],"number":[45],"elements,":[47],"two":[48],"which":[50],"are":[51],"acoustic":[53],"characteristics":[54],"model.":[61,191],"data":[63],"complex":[65,138],"changeable.":[67],"Most":[68],"methods":[69],"only":[70],"extract":[71,151],"single":[73,86,133],"type":[74],"feature":[76,87,134,147,197],"signal":[79],"to":[80,107,150],"represent":[81,137],"signal.":[84],"This":[85,110,141,157],"cannot":[88,135],"express":[89],"hidden":[91],"information.":[92,140],"And,":[93],"excellent":[95],"model":[98],"can":[99,226],"also":[100],"better":[101],"learn":[102],"characteristic":[104],"improve":[108,228,238],"performance.":[109,240],"work":[111,127,174],"proposes":[112,143],"new":[114],"method":[115],"for":[116],"First":[123],"all,":[125],"this":[126,173,193,242],"considers":[128],"problem":[130],"that":[131],"fully":[136],"paper":[142,243],"three":[144,159],"kinds":[145],"fusion":[148,161,196,212],"structures":[149],"from":[154],"different":[155,160],"angles.":[156],"extracts":[158],"features":[162,167,213,232],"based":[163],"low-level":[166],"higher-level":[169],"sparse":[170],"representation.":[171],"Secondly,":[172],"relies":[175],"strong":[178,219],"learning":[179],"ability":[180],"neural":[182],"network":[183,207],"weight":[186,223],"distribution":[187],"mechanism":[188],"attention":[190],"In":[192],"paper,":[194],"combined":[199],"with":[200,208,218],"bidirectional":[202],"long":[203],"short":[205],"memory":[206],"attention.":[209],"extracted":[211],"contain":[214],"discrimination.":[220],"When":[221],"increases,":[224],"it":[225],"further":[227],"influence":[230],"predicted":[235],"value":[236],"Finally,":[241],"carried":[245],"out":[246],"systematic":[247],"experiments":[248],"proposed":[251],"method,":[252],"results":[255],"verify":[256],"feasibility.":[258]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}