{"id":"https://openalex.org/W3175855533","doi":"https://doi.org/10.1109/icccs52626.2021.9449177","title":"Music Genre Classification with LSTM based on Time and Frequency Domain Features","display_name":"Music Genre Classification with LSTM based on Time and Frequency Domain Features","publication_year":2021,"publication_date":"2021-04-23","ids":{"openalex":"https://openalex.org/W3175855533","doi":"https://doi.org/10.1109/icccs52626.2021.9449177","mag":"3175855533"},"language":"en","primary_location":{"id":"doi:10.1109/icccs52626.2021.9449177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccs52626.2021.9449177","pdf_url":null,"source":{"id":"https://openalex.org/S4306498809","display_name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","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/A5036671587","display_name":"Yinhui Yi","orcid":"https://orcid.org/0000-0001-5332-4189"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yinhui Yi","raw_affiliation_strings":["School of Advanced Technology, Xi' an Jiaotong-Liverpool University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi' an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059827048","display_name":"Xiaohui Zhu","orcid":"https://orcid.org/0000-0003-1024-5442"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Zhu","raw_affiliation_strings":["School of Advanced Technology, Xi' an Jiaotong-Liverpool University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi' an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090256693","display_name":"Yong Yue","orcid":"https://orcid.org/0000-0001-7695-4538"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Yue","raw_affiliation_strings":["School of Advanced Technology, Xi' an Jiaotong-Liverpool University, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Advanced Technology, Xi' an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391780","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0001-8741-7180"},"institutions":[{"id":"https://openalex.org/I94611258","display_name":"Hebei Normal University","ror":"https://ror.org/004rbbw49","country_code":"CN","type":"education","lineage":["https://openalex.org/I94611258"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["College of Computer and Cyber Security, Hebei Normal University, Shijiazhuang, China"],"affiliations":[{"raw_affiliation_string":"College of Computer and Cyber Security, Hebei Normal University, Shijiazhuang, China","institution_ids":["https://openalex.org/I94611258"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036671587"],"corresponding_institution_ids":["https://openalex.org/I69356397"],"apc_list":null,"apc_paid":null,"fwci":2.4085,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.94291471,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"678","last_page":"682"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9937000274658203,"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":0.9907000064849854,"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":0.7658005356788635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7062479853630066},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7019315958023071},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6764460206031799},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6161940693855286},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6069622039794922},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.581885576248169},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5512215495109558},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5277134776115417},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.505357563495636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4962068200111389},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.47846341133117676},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.4384552836418152},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15655669569969177},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10628864169120789},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06404787302017212},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.06173643469810486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7658005356788635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7062479853630066},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7019315958023071},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6764460206031799},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6161940693855286},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6069622039794922},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.581885576248169},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5512215495109558},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5277134776115417},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.505357563495636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4962068200111389},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.47846341133117676},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.4384552836418152},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15655669569969177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10628864169120789},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06404787302017212},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.06173643469810486},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccs52626.2021.9449177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccs52626.2021.9449177","pdf_url":null,"source":{"id":"https://openalex.org/S4306498809","display_name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1508121828","https://openalex.org/W2050879753","https://openalex.org/W2064675550","https://openalex.org/W2101151533","https://openalex.org/W2107430826","https://openalex.org/W2113477260","https://openalex.org/W2133824856","https://openalex.org/W2136848157","https://openalex.org/W2563031223","https://openalex.org/W2571520038","https://openalex.org/W2890718983","https://openalex.org/W2963451564","https://openalex.org/W2976594877","https://openalex.org/W3004064628","https://openalex.org/W3015516707","https://openalex.org/W3017055680","https://openalex.org/W6630222583"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2372625757","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W4400265413","https://openalex.org/W4386218037"],"abstract_inverted_index":{"Deep":[0],"features":[1,28,37,67],"generated":[2],"from":[3,50],"deep":[4,27,74,96],"learning":[5],"models":[6],"contain":[7],"more":[8],"information":[9],"for":[10],"music":[11,31,51,91,110],"classification":[12],"than":[13],"short-term":[14,36],"features.":[15,75,97],"This":[16],"paper":[17],"uses":[18],"a":[19,57],"long-short":[20],"term":[21],"memory":[22],"(LSTM)":[23],"model":[24],"to":[25,70,72,88],"generate":[26,73],"and":[29,43,60,83],"achieve":[30],"genre":[32,92,111],"classification.":[33,112],"Firstly,":[34],"two":[35,66],"of":[38,109],"Zero":[39],"crossing":[40],"rate":[41],"(ZCR)":[42],"mel-frequency":[44],"spectral":[45],"coefficients":[46],"(MFCC)":[47],"are":[48,68],"extracted":[49],"in":[52],"digital":[53],"form,":[54],"which":[55],"is":[56],"time-domain":[58],"feature":[59],"frequency-domain":[61],"feature,":[62],"respectively.":[63],"Then":[64],"these":[65,95],"fed":[69],"LSTM":[71,103],"Finally,":[76],"we":[77],"use":[78],"support":[79],"vector":[80],"machine":[81],"(SVM)":[82],"k-nearest":[84],"neighbors":[85],"(KNN)":[86],"respectively":[87],"classify":[89],"the":[90,107],"based":[93],"on":[94],"Experimental":[98],"results":[99],"show":[100],"that":[101],"using":[102],"can":[104],"significantly":[105],"increase":[106],"accuracy":[108]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}