{"id":"https://openalex.org/W4400810078","doi":"https://doi.org/10.1109/ojcs.2024.3431229","title":"Musical Genre Classification Using Advanced Audio Analysis and Deep Learning Techniques","display_name":"Musical Genre Classification Using Advanced Audio Analysis and Deep Learning Techniques","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4400810078","doi":"https://doi.org/10.1109/ojcs.2024.3431229"},"language":"en","primary_location":{"id":"doi:10.1109/ojcs.2024.3431229","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3431229","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","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/ojcs.2024.3431229","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051351124","display_name":"Mumtahina Ahmed","orcid":"https://orcid.org/0000-0002-5602-9510"},"institutions":[{"id":"https://openalex.org/I4210147955","display_name":"Bangladesh University of Business and Technology","ror":"https://ror.org/0400am365","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210147955"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Mumtahina Ahmed","raw_affiliation_strings":["Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I4210147955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104852171","display_name":"Uland Rozario","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147955","display_name":"Bangladesh University of Business and Technology","ror":"https://ror.org/0400am365","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210147955"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Uland Rozario","raw_affiliation_strings":["Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I4210147955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109749546","display_name":"Md Mohshin Kabir","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md Mohshin Kabir","raw_affiliation_strings":["Faculty of Informatics, E&#x00F6;tv&#x00F6;s Lor&#x00E1;nd University, Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0001-9624-5499","affiliations":[{"raw_affiliation_string":"Faculty of Informatics, E&#x00F6;tv&#x00F6;s Lor&#x00E1;nd University, Budapest, Hungary","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005863795","display_name":"Zeyar Aung","orcid":"https://orcid.org/0000-0001-5990-9305"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Zeyar Aung","raw_affiliation_strings":["Department of Computer Science, Khalifa University, Abu Dhabi, UAE","Department of Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0001-5990-9305","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Khalifa University, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I176601375"]},{"raw_affiliation_string":"Department of Computer Science, Khalifa University, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I176601375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005221038","display_name":"Jungpil Shin","orcid":"https://orcid.org/0000-0002-7476-2468"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jungpil Shin","raw_affiliation_strings":["School of Computer Science and Engineering, The University of Aizu, Aizu-wakamatsu, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7476-2468","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, The University of Aizu, Aizu-wakamatsu, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071208302","display_name":"M. F. Mridha","orcid":"https://orcid.org/0000-0001-5738-1631"},"institutions":[{"id":"https://openalex.org/I103434671","display_name":"American International University-Bangladesh","ror":"https://ror.org/02j8ga255","country_code":"BD","type":"education","lineage":["https://openalex.org/I103434671"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"M. F. Mridha","raw_affiliation_strings":["Department of Computer Science and Engineering, American International University-Bangladesh, Dhaka, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0001-5738-1631","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, American International University-Bangladesh, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I103434671"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1750,"currency":"USD","value_usd":1750},"apc_paid":{"value":1750,"currency":"USD","value_usd":1750},"fwci":5.8087,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.96926175,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"5","issue":null,"first_page":"457","last_page":"467"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9416999816894531,"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":0.8099476099014282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5853502154350281},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5793846249580383},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5177925825119019},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5028302073478699},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4840816557407379},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4660989046096802},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.43504929542541504},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4271164536476135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41150087118148804},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40196746587753296},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.30918991565704346}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8099476099014282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5853502154350281},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5793846249580383},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5177925825119019},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5028302073478699},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4840816557407379},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4660989046096802},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.43504929542541504},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4271164536476135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41150087118148804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40196746587753296},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.30918991565704346},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ojcs.2024.3431229","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3431229","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3d1db445f02f48259f4db7796e9e251e","is_oa":true,"landing_page_url":"https://doaj.org/article/3d1db445f02f48259f4db7796e9e251e","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Open Journal of the Computer Society, Vol 5, Pp 457-467 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/ojcs.2024.3431229","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2024.3431229","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2111621157","https://openalex.org/W2127177652","https://openalex.org/W2133169093","https://openalex.org/W2133824856","https://openalex.org/W2137637927","https://openalex.org/W2167969117","https://openalex.org/W2191779130","https://openalex.org/W2340134902","https://openalex.org/W2395395217","https://openalex.org/W2529478963","https://openalex.org/W2593497185","https://openalex.org/W2774310041","https://openalex.org/W2884367656","https://openalex.org/W2896758169","https://openalex.org/W2901688232","https://openalex.org/W2902758295","https://openalex.org/W2931364255","https://openalex.org/W2963985474","https://openalex.org/W3011915764","https://openalex.org/W3110015897","https://openalex.org/W3154102786","https://openalex.org/W3160122420","https://openalex.org/W3169982272","https://openalex.org/W4200229038","https://openalex.org/W4225294434","https://openalex.org/W4292622404","https://openalex.org/W4293536249","https://openalex.org/W4317734114","https://openalex.org/W6682027195","https://openalex.org/W6704025895","https://openalex.org/W6713152820","https://openalex.org/W6728400142","https://openalex.org/W6761120048","https://openalex.org/W6786412761"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872","https://openalex.org/W3135448569"],"abstract_inverted_index":{"Classifying":[0],"music":[1,13,22,32,47,72,84,93,171],"genres":[2],"has":[3,192],"been":[4,193],"a":[5,26,43,61],"significant":[6],"problem":[7],"in":[8,31],"the":[9,69,78,90,119,125,188,196,202],"decade":[10],"of":[11,71,92,187],"seamless":[12],"streaming":[14],"platforms":[15],"and":[16,36,53,112,135,179,199],"countless":[17],"content":[18,34],"creations.":[19],"An":[20],"accurate":[21],"genre":[23,48,73,85,94],"classification":[24,49],"is":[25],"fundamental":[27],"task":[28,70],"with":[29,173],"applications":[30,178],"recommendation,":[33],"organization,":[35],"understanding":[37],"musical":[38],"trends.":[39],"This":[40,87,121],"study":[41,88,122],"presents":[42],"comprehensive":[44],"approach":[45],"to":[46,67,154,183],"using":[50,96,151],"deep":[51,62,163],"learning":[52,63,164],"advanced":[54],"audio":[55,133],"analysis":[56],"techniques.":[57],"In":[58],"this":[59,76,184],"study,":[60,77],"method":[64],"was":[65,81],"used":[66],"tackle":[68],"classification.":[74,86],"For":[75],"GTZAN":[79,189,197],"dataset":[80,198],"chosen":[82],"for":[83,169,175],"examines":[89],"challenge":[91],"categorization":[95],"Convolutional":[97],"Neural":[98,102],"Networks":[99,103],"(CNN),":[100],"Feedforward":[101],"(FNN),":[104],"Support":[105],"Vector":[106],"Machine":[107],"(SVM),":[108],"k-nearest":[109],"Neighbors":[110],"(kNN),":[111],"Long":[113],"Short-term":[114],"Memory":[115],"(LSTM)":[116],"models":[117,149],"on":[118,195,201],"dataset.":[120,205],"precisely":[123],"cross-validates":[124],"model's":[126],"output":[127],"following":[128],"feature":[129],"extraction":[130],"from":[131],"pre-processed":[132],"data":[134],"then":[136],"evaluates":[137],"its":[138,152],"performance.":[139],"The":[140],"modified":[141],"CNN":[142],"model":[143],"performs":[144],"better":[145],"than":[146],"conventional":[147],"NN":[148],"by":[150],"capacity":[153],"capture":[155],"complex":[156],"spectrogram":[157],"patterns.":[158],"These":[159],"results":[160],"highlight":[161],"how":[162],"algorithms":[165],"may":[166],"improve":[167],"systems":[168],"categorizing":[170],"genres,":[172],"implications":[174],"various":[176],"music-related":[177],"user":[180],"interfaces.":[181],"Up":[182],"point,":[185],"92.7%":[186],"dataset's":[190],"correctness":[191],"achieved":[194],"91.6%":[200],"ISMIR2004":[203],"Ballroom":[204]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
