{"id":"https://openalex.org/W7164907603","doi":"https://doi.org/10.1109/access.2026.3704285","title":"Automatic Sound Effect Classification and Subtitle Generation System Using Pre-Trained Audio Neural Networks With Transfer Learning","display_name":"Automatic Sound Effect Classification and Subtitle Generation System Using Pre-Trained Audio Neural Networks With Transfer Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7164907603","doi":"https://doi.org/10.1109/access.2026.3704285"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3704285","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3704285","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3704285","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138736244","display_name":"Hyeyoon Jung","orcid":"https://orcid.org/0009-0000-1461-1804"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeyoon Jung","raw_affiliation_strings":["Department of Information Convergence Engineering, Pusan National University, Busan, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-1461-1804","affiliations":[{"raw_affiliation_string":"Department of Information Convergence Engineering, Pusan National University, Busan, Republic of Korea","institution_ids":["https://openalex.org/I4921948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012263568","display_name":"Kyeongsu Byun","orcid":null},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyeongsu Byun","raw_affiliation_strings":["Department of Information Convergence Engineering, Pusan National University, Busan, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0001-9948-2550","affiliations":[{"raw_affiliation_string":"Department of Information Convergence Engineering, Pusan National University, Busan, Republic of Korea","institution_ids":["https://openalex.org/I4921948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081543046","display_name":"Joonho Kwon","orcid":"https://orcid.org/0000-0002-8207-9415"},"institutions":[{"id":"https://openalex.org/I4921948","display_name":"Pusan National University","ror":"https://ror.org/01an57a31","country_code":"KR","type":"education","lineage":["https://openalex.org/I4921948"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonho Kwon","raw_affiliation_strings":["Department of Data Science, Graduate School of Data Science, Pusan National University, Busan, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-8207-9415","affiliations":[{"raw_affiliation_string":"Department of Data Science, Graduate School of Data Science, Pusan National University, Busan, Republic of Korea","institution_ids":["https://openalex.org/I4921948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4921948"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88405966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"93352","last_page":"93369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.46619999408721924,"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/T11309","display_name":"Music and Audio Processing","score":0.46619999408721924,"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":0.09629999846220016,"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/T10863","display_name":"Voice and Speech Disorders","score":0.03480000048875809,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/subtitle","display_name":"Subtitle","score":0.7394000291824341},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6159999966621399},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5781999826431274},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4092000126838684},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.39910000562667847},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.35510000586509705},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3208000063896179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878000140190125},{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.7394000291824341},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6159999966621399},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5781999826431274},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5586000084877014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49970000982284546},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.39910000562667847},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.31779998540878296},{"id":"https://openalex.org/C2778488704","wikidata":"https://www.wikidata.org/wiki/Q15190726","display_name":"Audio equipment","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2779041454","wikidata":"https://www.wikidata.org/wiki/Q870780","display_name":"Chatbot","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3704285","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3704285","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:80073b0ba32e4817905212e3aa2a8b8d","is_oa":false,"landing_page_url":"https://doaj.org/article/80073b0ba32e4817905212e3aa2a8b8d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 93352-93369 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3704285","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3704285","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,48,181,197],"automatic":[3,80],"subtitle":[4,13,53,151,172,221],"generation":[5,14],"have":[6],"primarily":[7],"focused":[8],"on":[9,61,140],"speech":[10,185],"recognition,":[11],"whereas":[12],"for":[15,40,68,78,237],"nonverbal":[16,90,239],"sound":[17,91,113],"effects":[18],"has":[19],"received":[20],"comparatively":[21],"little":[22],"attention.":[23],"This":[24],"limitation":[25],"hinders":[26],"comprehensive":[27],"delivery":[28],"of":[29,85,89,112,168,175,229],"audiovisual":[30],"information.":[31],"Sound":[32],"effects—such":[33],"as":[34,202,233],"gunshots,":[35],"screams,":[36],"and":[37,44,64,83,108,125,144,157,170,186,193,205,208],"crying—are":[38],"crucial":[39],"providing":[41],"narrative":[42],"context":[43],"conveying":[45],"emotional":[46],"nuances":[47],"video":[49],"content.":[50],"Nevertheless,":[51],"current":[52],"systems":[54],"frequently":[55],"omit":[56],"these":[57],"elements,":[58],"relying":[59],"heavily":[60],"manual":[62],"annotation":[63],"underscoring":[65],"the":[66,79,122,160,226,230],"need":[67],"automated":[69],"approaches.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"propose":[75],"a":[76,86,97,129,171,234],"system":[77,95,162,232],"detection,":[81],"classification,":[82],"subtitling":[84],"broad":[87],"range":[88],"effects.":[92,114],"The":[93],"proposed":[94,161,231],"leverages":[96],"pretrained":[98,123],"audio":[99,116],"neural":[100],"network":[101],"model":[102,124],"via":[103],"transfer":[104],"learning":[105],"to":[106,132,149],"identify":[107],"classify":[109],"multiple":[110],"types":[111],"Collected":[115],"data":[117],"are":[118,137,147],"first":[119],"embedded":[120],"using":[121],"subsequently":[126],"processed":[127],"by":[128],"custom-designed":[130],"classifier":[131],"enhance":[133],"recognition":[134],"accuracy.":[135],"Subtitles":[136],"generated":[138],"based":[139],"time-aligned":[141],"sound-effect":[142,195],"detections,":[143],"consecutive":[145,214],"detections":[146],"merged":[148],"form":[150],"intervals.":[152],"Using":[153],"real":[154],"broadcast":[155],"videos":[156],"TV":[158],"content,":[159,200],"achieved":[163],"an":[164],"average":[165],"classification":[166],"accuracy":[167,174],"76%":[169],"timing":[173],"72.3%":[176],"within":[177],"3":[178],"seconds,":[179],"even":[180],"environments":[182],"with":[183,216],"overlapping":[184],"background":[187],"noise.":[188],"Our":[189],"approach":[190,236],"effectively":[191],"detects":[192],"classifies":[194],"events":[196],"diverse":[198],"media":[199],"such":[201],"dramas,":[203],"films,":[204],"entertainment":[206],"programs,":[207],"generates":[209],"corresponding":[210],"subtitles.":[211,244],"Furthermore,":[212],"merging":[213],"segments":[215],"identical":[217],"labels":[218],"helps":[219],"improve":[220],"coherence.":[222],"These":[223],"findings":[224],"demonstrate":[225],"practical":[227],"feasibility":[228],"subtitle-augmentation":[235],"incorporating":[238],"auditory":[240],"cues":[241],"into":[242],"dialogue-centered":[243]},"counts_by_year":[],"updated_date":"2026-06-28T08:01:55.173337","created_date":"2026-06-17T00:00:00"}