{"id":"https://openalex.org/W4410537621","doi":"https://doi.org/10.1109/kst65016.2025.11003373","title":"Multimodal Deep Learning for Y ouTube Stand-Up Comedy Transcription in Indonesian Language","display_name":"Multimodal Deep Learning for Y ouTube Stand-Up Comedy Transcription in Indonesian Language","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W4410537621","doi":"https://doi.org/10.1109/kst65016.2025.11003373"},"language":"en","primary_location":{"id":"doi:10.1109/kst65016.2025.11003373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kst65016.2025.11003373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 17th International Conference on Knowledge and Smart Technology (KST)","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/A5100611449","display_name":"Supriyono Supriyono","orcid":"https://orcid.org/0000-0002-4733-9189"},"institutions":[{"id":"https://openalex.org/I102893293","display_name":"State University of Malang","ror":"https://ror.org/00ypgyy34","country_code":"ID","type":"education","lineage":["https://openalex.org/I102893293"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Supriyono","raw_affiliation_strings":["Faculty of Engineering, Universitas Negeri Malang,Department of Electrical Engineering and Informatics,Malang,Indonesia,65145","Faculty of Letters, Universitas Negeri Malang,Department of Indonesian Literature,Malang,Indonesia,65145"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Universitas Negeri Malang,Department of Electrical Engineering and Informatics,Malang,Indonesia,65145","institution_ids":["https://openalex.org/I102893293"]},{"raw_affiliation_string":"Faculty of Letters, Universitas Negeri Malang,Department of Indonesian Literature,Malang,Indonesia,65145","institution_ids":["https://openalex.org/I102893293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076378305","display_name":"Aji Prasetya Wibawa","orcid":"https://orcid.org/0000-0002-6653-2697"},"institutions":[{"id":"https://openalex.org/I102893293","display_name":"State University of Malang","ror":"https://ror.org/00ypgyy34","country_code":"ID","type":"education","lineage":["https://openalex.org/I102893293"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Aji Prasetya Wibawa","raw_affiliation_strings":["Faculty of Engineering, Universitas Negeri Malang,Department of Electrical Engineering and Informatics,Malang,Indonesia,65145"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Universitas Negeri Malang,Department of Electrical Engineering and Informatics,Malang,Indonesia,65145","institution_ids":["https://openalex.org/I102893293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101993503","display_name":"Suyono Suyono","orcid":"https://orcid.org/0000-0001-9698-4363"},"institutions":[{"id":"https://openalex.org/I102893293","display_name":"State University of Malang","ror":"https://ror.org/00ypgyy34","country_code":"ID","type":"education","lineage":["https://openalex.org/I102893293"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Suyono","raw_affiliation_strings":["Faculty of Engineering, Universitas Negeri Malang,Department of Electrical Engineering and Informatics,Malang,Indonesia,65145","Faculty of Letters, Universitas Negeri Malang,Department of Indonesian Literature,Malang,Indonesia,65145"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Universitas Negeri Malang,Department of Electrical Engineering and Informatics,Malang,Indonesia,65145","institution_ids":["https://openalex.org/I102893293"]},{"raw_affiliation_string":"Faculty of Letters, Universitas Negeri Malang,Department of Indonesian Literature,Malang,Indonesia,65145","institution_ids":["https://openalex.org/I102893293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057557064","display_name":"Fachrul Kurniawan","orcid":"https://orcid.org/0000-0002-3709-8764"},"institutions":[{"id":"https://openalex.org/I3020190299","display_name":"Universitas Islam Negeri Maulana Malik Ibrahim","ror":"https://ror.org/03a8hhw69","country_code":"ID","type":"education","lineage":["https://openalex.org/I3020190299"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Fachrul Kurniawan","raw_affiliation_strings":["Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Maulana Malik Ibrahim,Malang,Indonesia,65144"],"affiliations":[{"raw_affiliation_string":"Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Maulana Malik Ibrahim,Malang,Indonesia,65144","institution_ids":["https://openalex.org/I3020190299"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100611449"],"corresponding_institution_ids":["https://openalex.org/I102893293"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1353719,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"358","last_page":"363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.8784999847412109,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.8784999847412109,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.8751000165939331,"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"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.8489999771118164,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/indonesian","display_name":"Indonesian","score":0.8492705821990967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5786169767379761},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5040956735610962},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4661363959312439},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.43173953890800476},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.40942785143852234},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08099719882011414}],"concepts":[{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.8492705821990967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5786169767379761},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5040956735610962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4661363959312439},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.43173953890800476},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.40942785143852234},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08099719882011414}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/kst65016.2025.11003373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/kst65016.2025.11003373","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 17th International Conference on Knowledge and Smart Technology (KST)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2963341956","https://openalex.org/W3016399951","https://openalex.org/W3029510736","https://openalex.org/W3039522238","https://openalex.org/W3092764814","https://openalex.org/W3110249671","https://openalex.org/W3122116274","https://openalex.org/W3162953990","https://openalex.org/W3173537093","https://openalex.org/W4200531086","https://openalex.org/W4205923520","https://openalex.org/W4210777681","https://openalex.org/W4220707319","https://openalex.org/W4225166635","https://openalex.org/W4229029890","https://openalex.org/W4281251145","https://openalex.org/W4285247782","https://openalex.org/W4293331281","https://openalex.org/W4313598181","https://openalex.org/W4322615422","https://openalex.org/W4365816927","https://openalex.org/W4377197105","https://openalex.org/W4382202377","https://openalex.org/W4383956687","https://openalex.org/W4385372118","https://openalex.org/W4385723810","https://openalex.org/W4386805190","https://openalex.org/W4387359882","https://openalex.org/W4387936432","https://openalex.org/W4390321749","https://openalex.org/W4390920066","https://openalex.org/W4391344842","https://openalex.org/W4391562260","https://openalex.org/W4391685690","https://openalex.org/W4391824278","https://openalex.org/W4391894220","https://openalex.org/W4392262358","https://openalex.org/W4392793612","https://openalex.org/W4393930293","https://openalex.org/W4399426288"],"related_works":["https://openalex.org/W4242621793","https://openalex.org/W648807974","https://openalex.org/W4229837155","https://openalex.org/W4236086937","https://openalex.org/W2294302573","https://openalex.org/W4312419881","https://openalex.org/W2086953810","https://openalex.org/W2512763533","https://openalex.org/W4248715694","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Transcribing":[0],"Indonesian":[1],"stand-up":[2,183],"comedy":[3],"poses":[4],"significant":[5],"challenges":[6,207],"due":[7],"to":[8,36,62,75,85,108,149,177,192],"its":[9,193],"dynamic":[10],"nature,":[11],"including":[12],"rapid":[13],"speech,":[14],"colloquialisms,":[15],"regional":[16],"dialects,":[17],"overlapping":[18],"dialogue,":[19],"and":[20,27,59,73,79,92,115,141,144,151,164,188,213,223],"non-verbal":[21,87,189],"humor":[22],"cues":[23],"such":[24,43],"as":[25],"gestures":[26],"facial":[28,90],"expressions.":[29],"Traditional":[30],"unimodal":[31],"transcription":[32,64,206,226],"methods":[33],"often":[34],"struggle":[35],"capture":[37],"the":[38,101,106,166,174,180,198],"full":[39],"contextual":[40,214],"richness":[41],"of":[42,97,182,200],"content.":[44],"This":[45,195],"study":[46],"introduces":[47],"a":[48,119,217],"novel":[49],"approach":[50,156],"by":[51,159,162,169],"employing":[52],"multimodal":[53,155,201],"deep":[54,202],"learning,":[55],"combining":[56],"both":[57,186],"auditory":[58],"visual":[60,80],"data":[61],"improve":[63],"accuracy.":[65],"The":[66,95,123,154],"model":[67,107],"processes":[68],"audio":[69],"streams":[70,81],"using":[71,128],"LSTM":[72],"Wav2Vec2":[74],"extract":[76],"linguistic":[77,212],"features":[78],"through":[82],"CNN":[83],"s":[84],"analyze":[86],"indicators":[88],"like":[89],"expressions":[91],"body":[93],"language.":[94],"integration":[96],"these":[98],"modalities":[99],"at":[100],"feature":[102],"fusion":[103],"stage":[104],"enables":[105],"better":[109],"understand":[110],"comedic":[111],"timing,":[112],"cultural":[113],"nuances,":[114],"humor-related":[116],"context,":[117],"yielding":[118],"more":[120,221],"comprehensive":[121],"transcription.":[122],"model's":[124,175],"performance":[125],"was":[126],"evaluated":[127],"standard":[129],"metrics":[130],"Word":[131],"Error":[132,136],"Rate":[133,137],"(WER),":[134],"Character":[135],"(CER),":[138],"F1":[139,167],"Score,":[140],"BLEU":[142],"Score":[143,168],"demonstrated":[145],"substantial":[146],"improvements":[147],"compared":[148],"audio-only":[150],"visual-only":[152],"models.":[153],"reduced":[157],"WER":[158],"37.45%,":[160],"CER":[161],"41.67%,":[163],"improved":[165],"13.58%.":[170],"These":[171],"results":[172],"highlight":[173],"ability":[176],"effectively":[178],"handle":[179],"complexities":[181],"comedy,":[184],"capturing":[185],"verbal":[187],"elements":[190],"essential":[191],"humor.":[194],"research":[196],"underscores":[197],"potential":[199],"learning":[203],"in":[204,208,227],"addressing":[205],"content":[209],"with":[210],"intricate":[211],"features,":[215],"offering":[216],"promising":[218],"solution":[219],"for":[220],"accurate":[222],"contextually":[224],"aware":[225],"multimedia":[228],"applications.":[229]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}