{"id":"https://openalex.org/W4402897164","doi":"https://doi.org/10.1109/sera61261.2024.10685563","title":"Multi Label Sound Classification using Deep Learning Models","display_name":"Multi Label Sound Classification using Deep Learning Models","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4402897164","doi":"https://doi.org/10.1109/sera61261.2024.10685563"},"language":"en","primary_location":{"id":"doi:10.1109/sera61261.2024.10685563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sera61261.2024.10685563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACIS 22nd International Conference on Software Engineering Research, Management and Applications (SERA)","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/A5094188246","display_name":"Tasnim Akter Onisha","orcid":null},"institutions":[{"id":"https://openalex.org/I39815113","display_name":"Georgia Southern University","ror":"https://ror.org/04agmb972","country_code":"US","type":"education","lineage":["https://openalex.org/I39815113"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tasnim Akter Onisha","raw_affiliation_strings":["Georgia Southern University,dept. Information Technology,Statesboro,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Southern University,dept. Information Technology,Statesboro,GA","institution_ids":["https://openalex.org/I39815113"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047923732","display_name":"Jongyeop Kim","orcid":"https://orcid.org/0000-0002-1068-9855"},"institutions":[{"id":"https://openalex.org/I39815113","display_name":"Georgia Southern University","ror":"https://ror.org/04agmb972","country_code":"US","type":"education","lineage":["https://openalex.org/I39815113"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jongyeop Kim","raw_affiliation_strings":["Georgia Southern University,dept. Information Technology,Statesboro,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Southern University,dept. Information Technology,Statesboro,GA","institution_ids":["https://openalex.org/I39815113"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045456815","display_name":"Jongho Seol","orcid":"https://orcid.org/0009-0007-4693-2507"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]},{"id":"https://openalex.org/I931969281","display_name":"Middle Georgia State College","ror":"https://ror.org/01cwqb692","country_code":"US","type":"education","lineage":["https://openalex.org/I931969281"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jongho Seol","raw_affiliation_strings":["Middle Georgia State University,dept. Information Technology,Macon,GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Middle Georgia State University,dept. Information Technology,Macon,GA","institution_ids":["https://openalex.org/I931969281","https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6114,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65917643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"129","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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/T10860","display_name":"Speech and Audio Processing","score":0.9677000045776367,"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":0.9463000297546387,"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":0.7222200632095337},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.6908799409866333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5284205079078674},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.48371532559394836},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48251578211784363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37474602460861206},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.355835884809494},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.346546471118927},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08991998434066772}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222200632095337},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.6908799409866333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5284205079078674},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.48371532559394836},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48251578211784363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37474602460861206},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.355835884809494},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.346546471118927},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08991998434066772},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sera61261.2024.10685563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sera61261.2024.10685563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACIS 22nd International Conference on Software Engineering Research, Management and Applications (SERA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W34562744","https://openalex.org/W1967690078","https://openalex.org/W2168441989","https://openalex.org/W2413158896","https://openalex.org/W2529337537","https://openalex.org/W2902444285","https://openalex.org/W2911484868","https://openalex.org/W2972598666","https://openalex.org/W3015177963","https://openalex.org/W3164035722","https://openalex.org/W4200473284","https://openalex.org/W4210523093","https://openalex.org/W4224277409","https://openalex.org/W4308087733"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W4375867731","https://openalex.org/W2909888262","https://openalex.org/W2611989081","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W4380075502","https://openalex.org/W4281776617"],"abstract_inverted_index":{"Accurate":[0],"and":[1,18,32,38,75,86,105,153,159],"automated":[2],"sound":[3,123],"classification":[4,46,124],"enables":[5],"a":[6,110],"strong":[7],"groundwork":[8],"for":[9,44,71,84,126,151],"diverse":[10],"advanced":[11],"deep":[12],"learning":[13],"applications":[14],"within":[15],"the":[16,25,61,68,106,117,121,140],"audio":[17,48,53,69,144,156],"music":[19],"domain.":[20],"This":[21],"study":[22],"focuses":[23],"on":[24,120],"application":[26],"of":[27,103,113,142],"Convolutional":[28],"Neural":[29],"Networks":[30],"(CNN)":[31],"combined":[33],"LSTM":[34],"(Long":[35],"Short-Term":[36],"Memory)":[37],"GRU":[39],"(Gated":[40],"Recurrent":[41],"unit)":[42],"models":[43],"instrument":[45,80,143],"from":[47,67],"signals,":[49],"contributing":[50],"to":[51,116,132],"intelligent":[52],"processing":[54,158],"systems.":[55],"Our":[56],"proposed":[57,96],"model":[58,108,119,133],"exclusively":[59],"utilizes":[60],"Mel-frequency":[62],"cepstral":[63],"coefficients":[64],"(MFCCs)":[65],"extraction":[66],"data":[70],"preprocessing.":[72],"A":[73],"large":[74],"complex":[76],"dataset,":[77],"including":[78],"Nineteen":[79],"classes":[81],"are":[82],"used":[83],"training":[85],"evaluation.":[87],"These":[88,146],"experimental":[89],"results":[90],"demonstrate":[91],"promising":[92],"performance,":[93],"with":[94],"our":[95],"CNN":[97,118],"architecture":[98],"achieving":[99],"an":[100],"impressive":[101],"accuracy":[102,112],"97%,":[104],"LSTM-GRU":[107],"achieves":[109],"lower":[111],"80%,":[114],"compared":[115],"multi-label":[122],"task":[125],"instruments":[127],"classes,":[128],"but":[129],"its":[130],"ability":[131],"temporal":[134],"dependencies":[135],"add":[136],"valuable":[137,149],"insights":[138,150],"into":[139],"dynamics":[141],"sequences.":[145],"findings":[147],"provide":[148],"researchers":[152],"practitioners":[154],"in":[155],"signal":[157],"machine":[160],"learning.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}