{"id":"https://openalex.org/W2128196382","doi":"https://doi.org/10.1109/tmm.2009.2017635","title":"Automatic Music Genre Classification Based on Modulation Spectral Analysis of Spectral and Cepstral Features","display_name":"Automatic Music Genre Classification Based on Modulation Spectral Analysis of Spectral and Cepstral Features","publication_year":2009,"publication_date":"2009-04-28","ids":{"openalex":"https://openalex.org/W2128196382","doi":"https://doi.org/10.1109/tmm.2009.2017635","mag":"2128196382"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2009.2017635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2009.2017635","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Multimedia","raw_type":"journal-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/A5010660600","display_name":"Chang-Hsing Lee","orcid":"https://orcid.org/0000-0002-5761-421X"},"institutions":[{"id":"https://openalex.org/I59460038","display_name":"Chung Hua University","ror":"https://ror.org/01yzz0f51","country_code":"TW","type":"education","lineage":["https://openalex.org/I59460038"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chang-Hsing Lee","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Chung Hua University, Hsinchu, Taiwan","Dept. of Comput. Sci. & Inf. Eng., Chung HuaUniversity, Hsinchu"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Chung Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I59460038"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Inf. Eng., Chung HuaUniversity, Hsinchu","institution_ids":["https://openalex.org/I59460038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109218512","display_name":"Jau-Ling Shih","orcid":null},"institutions":[{"id":"https://openalex.org/I59460038","display_name":"Chung Hua University","ror":"https://ror.org/01yzz0f51","country_code":"TW","type":"education","lineage":["https://openalex.org/I59460038"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jau-Ling Shih","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Chung Hua University, Hsinchu, Taiwan","Dept. of Comput. Sci. & Inf. Eng., Chung HuaUniversity, Hsinchu"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Chung Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I59460038"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Inf. Eng., Chung HuaUniversity, Hsinchu","institution_ids":["https://openalex.org/I59460038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101553990","display_name":"Kun-Ming Yu","orcid":"https://orcid.org/0000-0001-8706-3490"},"institutions":[{"id":"https://openalex.org/I59460038","display_name":"Chung Hua University","ror":"https://ror.org/01yzz0f51","country_code":"TW","type":"education","lineage":["https://openalex.org/I59460038"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kun-Ming Yu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Chung Hua University, Hsinchu, Taiwan","Dept. of Comput. Sci. & Inf. Eng., Chung HuaUniversity, Hsinchu"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Chung Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I59460038"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Inf. Eng., Chung HuaUniversity, Hsinchu","institution_ids":["https://openalex.org/I59460038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016644683","display_name":"Hwai-San Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I59460038","display_name":"Chung Hua University","ror":"https://ror.org/01yzz0f51","country_code":"TW","type":"education","lineage":["https://openalex.org/I59460038"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hwai-San Lin","raw_affiliation_strings":["Department of Computer Science and Information Engineering, Chung Hua University, Hsinchu, Taiwan","Dept. of Comput. Sci. & Inf. Eng., Chung HuaUniversity, Hsinchu"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, Chung Hua University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I59460038"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Inf. Eng., Chung HuaUniversity, Hsinchu","institution_ids":["https://openalex.org/I59460038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010660600"],"corresponding_institution_ids":["https://openalex.org/I59460038"],"apc_list":null,"apc_paid":null,"fwci":10.7355,"has_fulltext":false,"cited_by_count":150,"citation_normalized_percentile":{"value":0.98961247,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"11","issue":"4","first_page":"670","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":0.9998999834060669,"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":0.9998999834060669,"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":0.9876000285148621,"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":0.961899995803833,"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/spectrogram","display_name":"Spectrogram","score":0.8012698888778687},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.7855621576309204},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6832733750343323},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6582375168800354},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.585364580154419},{"id":"https://openalex.org/keywords/frequency-modulation","display_name":"Frequency modulation","score":0.5677690505981445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5656530261039734},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5630297660827637},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5447415709495544},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4443596601486206},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4381263256072998},{"id":"https://openalex.org/keywords/spectral-analysis","display_name":"Spectral analysis","score":0.41788196563720703},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4119025766849518},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2467716932296753},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15274915099143982},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.14909395575523376},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.11069503426551819}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8012698888778687},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.7855621576309204},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6832733750343323},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6582375168800354},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.585364580154419},{"id":"https://openalex.org/C11930861","wikidata":"https://www.wikidata.org/wiki/Q181417","display_name":"Frequency modulation","level":3,"score":0.5677690505981445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5656530261039734},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5630297660827637},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5447415709495544},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4443596601486206},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4381263256072998},{"id":"https://openalex.org/C2983668108","wikidata":"https://www.wikidata.org/wiki/Q280453","display_name":"Spectral analysis","level":3,"score":0.41788196563720703},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4119025766849518},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2467716932296753},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15274915099143982},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14909395575523376},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.11069503426551819},{"id":"https://openalex.org/C32891209","wikidata":"https://www.wikidata.org/wiki/Q483666","display_name":"Spectroscopy","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2009.2017635","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2009.2017635","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W131293899","https://openalex.org/W585519466","https://openalex.org/W1560013842","https://openalex.org/W1607425652","https://openalex.org/W1797428404","https://openalex.org/W1971332722","https://openalex.org/W1992272902","https://openalex.org/W1998176629","https://openalex.org/W2028735910","https://openalex.org/W2028819669","https://openalex.org/W2041638389","https://openalex.org/W2101252291","https://openalex.org/W2103253424","https://openalex.org/W2113484761","https://openalex.org/W2117717972","https://openalex.org/W2125324924","https://openalex.org/W2127177652","https://openalex.org/W2129351839","https://openalex.org/W2133824856","https://openalex.org/W2136623223","https://openalex.org/W2136951780","https://openalex.org/W2139435939","https://openalex.org/W2140266719","https://openalex.org/W2140539262","https://openalex.org/W2142183264","https://openalex.org/W2142236629","https://openalex.org/W2148086858","https://openalex.org/W2148748626","https://openalex.org/W2154221499","https://openalex.org/W2158275940","https://openalex.org/W2159561775","https://openalex.org/W2161036973","https://openalex.org/W2163759924","https://openalex.org/W2167969117","https://openalex.org/W2799061466","https://openalex.org/W3021310968","https://openalex.org/W3034415380","https://openalex.org/W4244494905","https://openalex.org/W4250499635","https://openalex.org/W6605236737","https://openalex.org/W6638333121","https://openalex.org/W6681044243","https://openalex.org/W6682080903","https://openalex.org/W6684264527","https://openalex.org/W6779561511"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W2066371342"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"will":[4,37],"propose":[5],"an":[6],"automatic":[7],"music":[8,64,140],"genre":[9],"classification":[10,133,151],"approach":[11,115,147],"based":[12],"on":[13,137],"long-term":[14],"modulation":[15,41,46,54,67,75,78,83,92,110],"spectral":[16,19,31,79,84],"analysis":[17,32],"of":[18,33,63,103,108],"(OSC":[20],"and":[21,43,82,95,106,123],"MPEG-7":[22],"NASE)":[23],"as":[24,26],"well":[25],"cepstral":[27],"(MFCC)":[28],"features.":[29],"Modulation":[30],"every":[34],"feature":[35,119],"value":[36],"generate":[38],"a":[39,53],"corresponding":[40],"spectrum":[42,68],"all":[44,109],"the":[45,58,104,132,157],"spectra":[47],"can":[48,148],"be":[49],"collected":[50],"to":[51,130],"form":[52],"spectrogram":[55],"which":[56,116],"exhibits":[57],"time-varying":[59],"or":[60],"rhythmic":[61],"information":[62,113],"signals.":[65],"Each":[66],"is":[69,128],"then":[70,88],"decomposed":[71],"into":[72],"several":[73],"logarithmically-spaced":[74],"subbands.":[76,111],"The":[77],"contrast":[80],"(MSC)":[81],"valley":[85],"(MSV)":[86],"are":[87,98],"computed":[89],"from":[90,100],"each":[91],"subband.":[93],"Effective":[94],"compact":[96],"features":[97],"generated":[99],"statistical":[101],"aggregations":[102],"MSCs":[105],"MSVs":[107],"An":[112],"fusion":[114,121],"integrates":[117],"both":[118],"level":[120,125],"method":[122,127],"decision":[124],"combination":[126],"employed":[129],"improve":[131],"accuracy.":[134],"Experiments":[135],"conducted":[136],"two":[138],"different":[139],"datasets":[141],"have":[142],"shown":[143],"that":[144],"our":[145],"proposed":[146],"achieve":[149],"higher":[150],"accuracy":[152],"than":[153],"other":[154],"approaches":[155],"with":[156],"same":[158],"experimental":[159],"setup.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":9}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
