{"id":"https://openalex.org/W4404609288","doi":"https://doi.org/10.1109/icmlca63499.2024.10753693","title":"A Hybrid CNN-LSTM Architecture for Enhanced Music Genre Classification","display_name":"A Hybrid CNN-LSTM Architecture for Enhanced Music Genre Classification","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4404609288","doi":"https://doi.org/10.1109/icmlca63499.2024.10753693"},"language":"en","primary_location":{"id":"doi:10.1109/icmlca63499.2024.10753693","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmlca63499.2024.10753693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 5th International Conference on Machine Learning and Computer Application (ICMLCA)","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/A5101692801","display_name":"Xiaoyu Xie","orcid":"https://orcid.org/0000-0003-1234-1032"},"institutions":[{"id":"https://openalex.org/I4210114235","display_name":"Heihe University","ror":"https://ror.org/0221fhj86","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210114235"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyu Xie","raw_affiliation_strings":["Heihe University,Heihe City,China"],"affiliations":[{"raw_affiliation_string":"Heihe University,Heihe City,China","institution_ids":["https://openalex.org/I4210114235"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101692801"],"corresponding_institution_ids":["https://openalex.org/I4210114235"],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71993789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"72","last_page":"75"},"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/T13996","display_name":"Diverse Musicological Studies","score":0.9440000057220459,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9009000062942505,"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":0.7950388789176941},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6492472887039185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5262994766235352},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4395579695701599},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.4200839698314667},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40639349818229675},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3800444006919861},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15124189853668213},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.06879615783691406},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.062093377113342285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950388789176941},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6492472887039185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5262994766235352},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4395579695701599},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.4200839698314667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40639349818229675},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3800444006919861},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15124189853668213},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.06879615783691406},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.062093377113342285}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlca63499.2024.10753693","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmlca63499.2024.10753693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 5th International Conference on Machine Learning and Computer Application (ICMLCA)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2039871688","https://openalex.org/W2588198209","https://openalex.org/W1909006023","https://openalex.org/W4205824991","https://openalex.org/W3200723557","https://openalex.org/W2883491016","https://openalex.org/W4312713546","https://openalex.org/W2362195430","https://openalex.org/W4205999209","https://openalex.org/W2735080633"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"study":[4],"on":[5,55],"the":[6,42,62,84],"effectiveness":[7],"of":[8,86],"integrating":[9],"Convolutional":[10],"Neural":[11],"Networks":[12],"(CNN)":[13],"and":[14,79],"Long":[15],"Short-Term":[16],"Memory":[17],"(LSTM)":[18],"networks":[19],"for":[20],"music":[21,58],"genre":[22,91],"classification.":[23],"By":[24],"combining":[25],"CNN's":[26],"ability":[27],"to":[28,38],"extract":[29],"spatial":[30],"features":[31],"from":[32],"audio":[33],"data":[34],"with":[35,72],"LSTM's":[36],"capacity":[37],"capture":[39],"temporal":[40,74],"dependencies,":[41],"hybrid":[43],"CNN-LSTM":[44],"model":[45],"shows":[46],"superior":[47],"performance":[48],"over":[49],"traditional":[50],"models.":[51],"The":[52,81],"experiments":[53],"conducted":[54],"ten":[56],"different":[57],"genres":[59,71],"demonstrate":[60],"that":[61],"proposed":[63],"approach":[64],"achieves":[65],"higher":[66],"classification":[67,92],"accuracy,":[68],"particularly":[69],"in":[70,89],"complex":[73],"structures":[75],"like":[76],"Rock,":[77],"Pop,":[78],"Hip-Hop.":[80],"results":[82],"highlight":[83],"potential":[85],"this":[87],"architecture":[88],"improving":[90],"tasks.":[93]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}