{"id":"https://openalex.org/W1146734363","doi":"https://doi.org/10.1145/2801127","title":"Combining Acoustic and Multilevel Visual Features for Music Genre Classification","display_name":"Combining Acoustic and Multilevel Visual Features for Music Genre Classification","publication_year":2015,"publication_date":"2015-08-24","ids":{"openalex":"https://openalex.org/W1146734363","doi":"https://doi.org/10.1145/2801127","mag":"1146734363"},"language":"en","primary_location":{"id":"doi:10.1145/2801127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2801127","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5001137398","display_name":"Ming-Ju Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Ju Wu","raw_affiliation_strings":["National Taiwan University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073451247","display_name":"Jyh\u2010Shing Roger Jang","orcid":"https://orcid.org/0000-0002-7319-9095"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Shing R. Jang","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":3.1266,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.91976034,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"12","issue":"1","first_page":"1","last_page":"17"},"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":0.9940999746322632,"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":0.9854999780654907,"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":0.6950324773788452},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6912944912910461},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.688963770866394},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5347840785980225},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5316147208213806},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5085057020187378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4927120506763458},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4220011830329895},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.07035693526268005}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6950324773788452},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912944912910461},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.688963770866394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5347840785980225},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5316147208213806},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5085057020187378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4927120506763458},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4220011830329895},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.07035693526268005},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2801127","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2801127","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W200160492","https://openalex.org/W395933519","https://openalex.org/W807698299","https://openalex.org/W1510526001","https://openalex.org/W1556219185","https://openalex.org/W1560013842","https://openalex.org/W1966311970","https://openalex.org/W2027035856","https://openalex.org/W2030788302","https://openalex.org/W2041823554","https://openalex.org/W2052872069","https://openalex.org/W2056680352","https://openalex.org/W2070292941","https://openalex.org/W2100753110","https://openalex.org/W2100969003","https://openalex.org/W2101252291","https://openalex.org/W2107430826","https://openalex.org/W2107642652","https://openalex.org/W2110681820","https://openalex.org/W2120803704","https://openalex.org/W2125324924","https://openalex.org/W2126271732","https://openalex.org/W2127566601","https://openalex.org/W2128196382","https://openalex.org/W2133824856","https://openalex.org/W2137992478","https://openalex.org/W2144383041","https://openalex.org/W2147147599","https://openalex.org/W2148748626","https://openalex.org/W2153635508","https://openalex.org/W2154473523","https://openalex.org/W2158275940","https://openalex.org/W2163352848","https://openalex.org/W2164291616","https://openalex.org/W2290845176","https://openalex.org/W2296248436","https://openalex.org/W2390689188","https://openalex.org/W2399467590","https://openalex.org/W2540121965","https://openalex.org/W2604292070","https://openalex.org/W2997546679"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W1481643945","https://openalex.org/W2153275212","https://openalex.org/W2402674073","https://openalex.org/W2328848613","https://openalex.org/W3135448569"],"abstract_inverted_index":{"Most":[0],"music":[1,30,100,121],"genre":[2,101],"classification":[3,102],"approaches":[4],"extract":[5],"acoustic":[6,55,115],"features":[7,37,118],"from":[8,104],"frames":[9],"to":[10,15,106],"capture":[11],"timbre":[12],"information,":[13],"leading":[14],"the":[16,54,64,77,89,93,109],"common":[17],"framework":[18],"of":[19,71,113],"bag-of-frames":[20],"analysis.":[21],"However,":[22],"time-frequency":[23],"analysis":[24],"is":[25,50],"also":[26],"vital":[27],"for":[28,38,52,119],"modeling":[29],"genres.":[31,122],"This":[32],"article":[33],"proposes":[34],"multilevel":[35],"visual":[36,57,117],"extracting":[39],"spectrogram":[40],"textures":[41],"and":[42,56,74,83,111,116],"their":[43],"temporal":[44],"variations.":[45],"A":[46],"confidence-based":[47],"late":[48],"fusion":[49],"proposed":[51,65,90],"combining":[53,114],"features.":[58],"The":[59],"experimental":[60],"results":[61],"indicated":[62],"that":[63],"method":[66],"achieved":[67],"an":[68],"accuracy":[69],"improvement":[70],"approximately":[72],"14%":[73],"2%":[75],"in":[76],"world's":[78],"largest":[79],"benchmark":[80],"dataset":[81],"(MASD)":[82],"Unique":[84],"dataset,":[85],"respectively.":[86],"In":[87],"particular,":[88],"approach":[91],"won":[92],"Music":[94],"Information":[95],"Retrieval":[96],"Evaluation":[97],"eXchange":[98],"(MIREX)":[99],"contests":[103],"2011":[105],"2013,":[107],"demonstrating":[108],"feasibility":[110],"necessity":[112],"classifying":[120]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
