{"id":"https://openalex.org/W2117717972","doi":"https://doi.org/10.1109/icassp.2004.1326806","title":"A comparison of human and automatic musical genre classification","display_name":"A comparison of human and automatic musical genre classification","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2117717972","doi":"https://doi.org/10.1109/icassp.2004.1326806","mag":"2117717972"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5001736738","display_name":"Saskia Lippens","orcid":"https://orcid.org/0000-0002-8261-3462"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"S. Lippens","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University, Gent, Belgium","Dept. of Electron. & Information Syst., Ghent Univ., Gent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Dept. of Electron. & Information Syst., Ghent Univ., Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109066479","display_name":"J.-P. Martens","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"J.P. Martens","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University, Gent, Belgium","Dept. of Electron. & Information Syst., Ghent Univ., Gent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Dept. of Electron. & Information Syst., Ghent Univ., Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070960789","display_name":"Tom De Mulder","orcid":"https://orcid.org/0000-0003-0823-105X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"T. De Mulder","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University, Gent, Belgium","Dept. of Electron. & Information Syst., Ghent Univ., Gent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Dept. of Electron. & Information Syst., Ghent Univ., Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"iv","last_page":"233"},"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":0.9983999729156494,"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":0.9962999820709229,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8250856399536133},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.794176459312439},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6149494051933289},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.5859614014625549},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.5545267462730408},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49568474292755127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49551212787628174},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42749476432800293},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.42044925689697266},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4155743420124054}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8250856399536133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794176459312439},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6149494051933289},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.5859614014625549},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.5545267462730408},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49568474292755127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49551212787628174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42749476432800293},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.42044925689697266},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4155743420124054},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1326806","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:404062","is_oa":false,"landing_page_url":"http://hdl.handle.net/1854/LU-404062","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 0-7803-8484-9","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1595803501","https://openalex.org/W1774234760","https://openalex.org/W1989164285","https://openalex.org/W2054795546","https://openalex.org/W2133824856","https://openalex.org/W2136564616","https://openalex.org/W2138781314","https://openalex.org/W2140266719","https://openalex.org/W2148154194","https://openalex.org/W2159561775","https://openalex.org/W2799061466","https://openalex.org/W3034415380","https://openalex.org/W4244494905","https://openalex.org/W6635759712","https://openalex.org/W6779561511"],"related_works":["https://openalex.org/W2736574136","https://openalex.org/W2038216521","https://openalex.org/W4399693842","https://openalex.org/W2399955410","https://openalex.org/W3126677997","https://openalex.org/W2565286512","https://openalex.org/W2097377227","https://openalex.org/W2933782699","https://openalex.org/W4317383455","https://openalex.org/W3129283347"],"abstract_inverted_index":{"Recently":[0],"there":[1,104],"has":[2],"been":[3],"an":[4,136],"increasing":[5],"amount":[6],"of":[7,12,16,49,59,71,81,87],"work":[8,83],"in":[9,18,73],"the":[10,45,56,85,88,96],"area":[11],"automatic":[13,74,89,124],"genre":[14,50,60,76,93,109],"classification":[15,30,51,110],"music":[17,27],"audio":[19],"format.":[20],"In":[21,64],"addition":[22],"to":[23,37],"automatically":[24],"structuring":[25],"large":[26],"collections":[28],"such":[29],"can":[31,118],"be":[32,120],"used":[33],"as":[34],"a":[35,69],"way":[36],"evaluate":[38],"features":[39,133,143],"for":[40,107],"describing":[41],"musical":[42,75],"content.":[43],"However":[44],"evaluation":[46],"and":[47,114],"comparison":[48,86],"systems":[52],"is":[53,84,105,111],"hindered":[54],"by":[55,62],"subjective":[57,113],"perception":[58],"definitions":[61],"users.":[63],"this":[65,82],"work,":[66],"we":[67],"describe":[68],"set":[70],"experiments":[72,129],"classification.":[77,127],"An":[78],"important":[79],"contribution":[80],"results":[90,100,117],"with":[91,142],"human":[92,126],"classifications":[94],"on":[95,145],"same":[97],"dataset.":[98],"The":[99,128],"show":[101,131],"that,":[102],"although":[103],"room":[106],"improvement,":[108],"inherently":[112],"therefore":[115],"perfect":[116],"not":[119],"expected":[121],"neither":[122],"from":[123,135],"nor":[125],"also":[130],"that":[132],"derived":[134],"auditory":[137],"model":[138],"have":[139],"similar":[140],"performance":[141],"based":[144],"mel-frequency":[146],"cepstral":[147],"coefficients":[148],"(MFCC).":[149]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
