{"id":"https://openalex.org/W3085356816","doi":"https://doi.org/10.1145/3408127.3408137","title":"Music Genre Classification with Transformer Classifier","display_name":"Music Genre Classification with Transformer Classifier","publication_year":2020,"publication_date":"2020-06-19","ids":{"openalex":"https://openalex.org/W3085356816","doi":"https://doi.org/10.1145/3408127.3408137","mag":"3085356816"},"language":"en","primary_location":{"id":"doi:10.1145/3408127.3408137","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3408127.3408137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","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/A5114143672","display_name":"Yingying Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yingying Zhuang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017107368","display_name":"Yuezhang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuezhang Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101811770","display_name":"Jie Zheng","orcid":"https://orcid.org/0000-0003-2402-1263"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zheng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114143672"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":2.5761,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.90447663,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9965000152587891,"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/T10860","display_name":"Speech and Audio Processing","score":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7590376138687134},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6436775922775269},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6273126602172852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5392763614654541},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4574616849422455},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4244210720062256},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38368257880210876},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12001597881317139},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.09026247262954712}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7590376138687134},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6436775922775269},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6273126602172852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5392763614654541},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4574616849422455},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4244210720062256},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38368257880210876},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12001597881317139},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.09026247262954712},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3408127.3408137","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3408127.3408137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W170732776","https://openalex.org/W1583001605","https://openalex.org/W1973746598","https://openalex.org/W2012665501","https://openalex.org/W2013020033","https://openalex.org/W2014470830","https://openalex.org/W2023425980","https://openalex.org/W2059652044","https://openalex.org/W2071103260","https://openalex.org/W2098950531","https://openalex.org/W2103869314","https://openalex.org/W2107430826","https://openalex.org/W2107789863","https://openalex.org/W2133824856","https://openalex.org/W2137028279","https://openalex.org/W2145487065","https://openalex.org/W2167969117","https://openalex.org/W2212492883","https://openalex.org/W2267186426","https://openalex.org/W2583684860","https://openalex.org/W2626778328","https://openalex.org/W2756184659","https://openalex.org/W2963451564","https://openalex.org/W6653477362"],"related_works":["https://openalex.org/W2309093070","https://openalex.org/W2794946013","https://openalex.org/W4310420093","https://openalex.org/W2982642565","https://openalex.org/W2241738664","https://openalex.org/W3154635860","https://openalex.org/W4226332880","https://openalex.org/W4298054035","https://openalex.org/W2113421559","https://openalex.org/W3164111940"],"abstract_inverted_index":{"Music":[0,10,20,111],"Genre":[1,21,112],"Classification":[2,22],"is":[3,15,41],"a":[4,79,92],"significant":[5],"and":[6,52,106],"practical":[7],"field":[8],"of":[9,33,47],"Information":[11],"Retrieval.":[12],"Deep":[13],"learning":[14,73],"increasingly":[16],"being":[17],"applied":[18],"to":[19,65],"for":[23],"two":[24],"main":[25],"reasons.":[26],"Firstly,":[27],"it":[28],"avoids":[29],"the":[30,38,44,50,99],"manual":[31],"selection":[32],"audio":[34,103],"signal":[35],"features.":[36],"Secondly,":[37],"hierarchical":[39],"topology":[40],"consistent":[42],"with":[43],"layering":[45],"structure":[46],"music":[48,67],"in":[49,78,85,110],"time":[51],"frequency":[53],"domains.":[54],"The":[55,95],"existing":[56],"work":[57],"used":[58],"CNNs":[59],"or":[60,62],"RNNs":[61],"their":[63],"combination":[64],"classify":[66],"genre,":[68],"which":[69],"have":[70],"limitations":[71],"on":[72],"dependencies":[74],"between":[75,101],"distant":[76],"positions":[77],"sequence.":[80],"Inspired":[81],"by":[82],"an":[83],"advance":[84],"Natural":[86],"Language":[87],"Processing":[88],"(NLP),":[89],"we":[90],"designed":[91],"Transformer":[93,96],"classifier.":[94],"classifier":[97],"analyzes":[98],"relationship":[100],"different":[102],"frames":[104],"well":[105],"achieves":[107],"better":[108],"performance":[109],"Classification.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}