{"id":"https://openalex.org/W2094146179","doi":"https://doi.org/10.1145/1937728.1937772","title":"Music genre classification based on MPEG-7 audio features","display_name":"Music genre classification based on MPEG-7 audio features","publication_year":2010,"publication_date":"2010-12-30","ids":{"openalex":"https://openalex.org/W2094146179","doi":"https://doi.org/10.1145/1937728.1937772","mag":"2094146179"},"language":"en","primary_location":{"id":"doi:10.1145/1937728.1937772","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1937728.1937772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second International Conference on Internet Multimedia Computing and Service","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/A5100448208","display_name":"Song Li","orcid":"https://orcid.org/0000-0002-7961-8502"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Song Li","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Harbin Institute of Technology Harbin, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Harbin, China#TAB#","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398343","display_name":"Haifeng Li","orcid":"https://orcid.org/0000-0002-2534-2299"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Li","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Harbin Institute of Technology Harbin, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Harbin, China#TAB#","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018662596","display_name":"Lin Ma","orcid":"https://orcid.org/0000-0003-1684-9714"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Ma","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Harbin Institute of Technology Harbin, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Harbin, China#TAB#","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100448208"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.16833096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"185","last_page":"188"},"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":0.9975000023841858,"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":0.9825999736785889,"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":0.7617684006690979},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7280762791633606},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6242300271987915},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5675614476203918},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.5386632680892944},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4980783462524414},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4761195778846741},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.46582624316215515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44244733452796936},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4421972632408142},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4363609552383423},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42404744029045105},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3398802876472473}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617684006690979},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7280762791633606},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6242300271987915},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5675614476203918},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.5386632680892944},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4980783462524414},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4761195778846741},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.46582624316215515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44244733452796936},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4421972632408142},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4363609552383423},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42404744029045105},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3398802876472473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1937728.1937772","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1937728.1937772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second International Conference on Internet Multimedia Computing and Service","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4491470859","display_name":null,"funder_award_id":"20050213032","funder_id":"https://openalex.org/F4320321106","funder_display_name":"Ministry of Education of the People's Republic of China"},{"id":"https://openalex.org/G7625243973","display_name":null,"funder_award_id":"60772076","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1508121828","https://openalex.org/W2120599713","https://openalex.org/W2123497171","https://openalex.org/W2139435939","https://openalex.org/W2144894928","https://openalex.org/W2578590866","https://openalex.org/W6680890615"],"related_works":["https://openalex.org/W2048014685","https://openalex.org/W3009295899","https://openalex.org/W2370972896","https://openalex.org/W2289868279","https://openalex.org/W2555630001","https://openalex.org/W1546240199","https://openalex.org/W2109142991","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293"],"abstract_inverted_index":{"Music":[0],"genre":[1,52],"is":[2,13],"a":[3,40],"useful":[4],"tool":[5],"which":[6],"can":[7],"categorize":[8],"large":[9],"music":[10,29,51,98],"database.":[11],"MPEG-7":[12,21,47],"an":[14],"international":[15],"standard":[16],"for":[17,26,50],"managing":[18],"audiovisual":[19],"contents.":[20],"audio":[22,27,48],"features":[23,49],"are":[24,87],"used":[25],"classification,":[28],"instrument":[30],"classification":[31,53],"and":[32,74,82],"speech":[33],"recognition.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,59],"present":[39],"series":[41],"of":[42,77,93,97],"experiments":[43],"to":[44],"evaluate":[45],"the":[46,56,75],"performance.":[54],"For":[55],"feature":[57],"extraction,":[58],"choose":[60],"Mel-scale":[61],"Frequency":[62],"Cepstrum":[63],"Coefficients":[64],"(MFCC),":[65],"Audio":[66,70,78],"Spectrum":[67,71,79],"Envelop":[68],"(ASE),":[69],"Projection":[72],"(ASP)":[73],"combination":[76],"Centroid,":[80],"Spread":[81],"Flatness.":[83],"Some":[84],"comparable":[85],"results":[86],"derived":[88],"from":[89],"our":[90],"database":[91],"consisting":[92],"7":[94],"different":[95],"genres":[96],"with":[99],"Gaussian":[100],"Mixture":[101],"Model":[102],"(GMM)":[103],"classifier.":[104]},"counts_by_year":[{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
