{"id":"https://openalex.org/W4399418604","doi":"https://doi.org/10.1145/3651671.3651696","title":"Music style classification by jointly using CNN and Transformer","display_name":"Music style classification by jointly using CNN and Transformer","publication_year":2024,"publication_date":"2024-02-02","ids":{"openalex":"https://openalex.org/W4399418604","doi":"https://doi.org/10.1145/3651671.3651696"},"language":"en","primary_location":{"id":"doi:10.1145/3651671.3651696","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651671.3651696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","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/A5088825610","display_name":"Rui Tang","orcid":"https://orcid.org/0009-0000-6476-2758"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Tang","raw_affiliation_strings":["Northeast Normal University, China"],"raw_orcid":"https://orcid.org/0009-0000-6476-2758","affiliations":[{"raw_affiliation_string":"Northeast Normal University, China","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101535006","display_name":"Miao Qi","orcid":"https://orcid.org/0000-0002-5932-4435"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Qi","raw_affiliation_strings":["Northeast Normal University, China"],"raw_orcid":"https://orcid.org/0000-0002-5932-4435","affiliations":[{"raw_affiliation_string":"Northeast Normal University, China","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046432750","display_name":"Nanqing Wang","orcid":"https://orcid.org/0009-0009-9712-9794"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nanqing Wang","raw_affiliation_strings":["Changchun Humanities and Sciences College, China"],"raw_orcid":"https://orcid.org/0009-0009-9712-9794","affiliations":[{"raw_affiliation_string":"Changchun Humanities and Sciences College, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088825610"],"corresponding_institution_ids":["https://openalex.org/I184983240"],"apc_list":null,"apc_paid":null,"fwci":0.3288,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50071569,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"707","last_page":"712"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9887999892234802,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9876999855041504,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7822813391685486},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6595826745033264},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6392991542816162},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5570679903030396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.507026195526123},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4808010160923004},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4506887197494507},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34800782799720764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822813391685486},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6595826745033264},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6392991542816162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5570679903030396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.507026195526123},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4808010160923004},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4506887197494507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34800782799720764},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3651671.3651696","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651671.3651696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2008056655","https://openalex.org/W2064675550","https://openalex.org/W2172140247","https://openalex.org/W2612445135","https://openalex.org/W3035414587","https://openalex.org/W3036601975","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3138516171","https://openalex.org/W3180663620","https://openalex.org/W4224980507","https://openalex.org/W4254816979","https://openalex.org/W4310873011","https://openalex.org/W4372341324","https://openalex.org/W4386047745","https://openalex.org/W6788611029","https://openalex.org/W6810108138"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W2811106690","https://openalex.org/W4239306820","https://openalex.org/W2947043951","https://openalex.org/W4312417841","https://openalex.org/W4210874298"],"abstract_inverted_index":{"Music":[0],"influences":[1],"people":[2],"in":[3,11,44],"many":[4],"ways":[5],"and":[6,85,114,134],"plays":[7],"an":[8],"important":[9],"role":[10],"human":[12],"life":[13],"from":[14,38],"emotional":[15],"expression":[16],"to":[17,20,32,89],"social":[18],"interaction":[19],"cognitive":[21],"development.":[22],"However,":[23],"the":[24,45,103,122],"variety":[25],"of":[26,47,56,102,112,125],"musical":[27],"styles":[28],"is":[29,71,106,135],"often":[30],"difficult":[31],"distinguish.":[33],"In":[34],"this":[35],"paper,":[36],"different":[37],"existing":[39,139],"methods":[40,141],"that":[41,121],"music":[42,67,75,97],"presented":[43],"form":[46],"audio":[48,76,78,93],"information":[49],"can":[50,129],"be":[51],"classified":[52],"as":[53],"a":[54,65,109],"sequence":[55],"features":[57,95],"divided":[58],"by":[59,73,108],"time":[60],"through":[61],"RNN":[62],"or":[63],"LSTM,":[64],"novel":[66],"style":[68,98],"classification":[69,123,132,140],"method":[70,105,128],"proposed":[72,104,127],"transforming":[74],"into":[77],"image.":[79],"Moreover,":[80],"Convolutional":[81],"Neural":[82],"Network":[83],"(CNN)":[84],"Transformer":[86],"are":[87],"combined":[88],"jointly":[90],"extract":[91],"rich":[92],"image":[94],"for":[96],"classification.":[99],"The":[100,117],"effectiveness":[101],"evaluated":[107],"large":[110],"number":[111],"ablation":[113],"comparative":[115],"experiments.":[116],"experimental":[118],"results":[119],"demonstrate":[120],"accuracy":[124,133],"our":[126],"achieve":[130],"satisfactory":[131],"better":[136],"than":[137],"some":[138],"on":[142],"GTZAN":[143],"dataset.":[144]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}