{"id":"https://openalex.org/W1980599288","doi":"https://doi.org/10.1145/2324796.2324859","title":"Supervised dictionary learning for music genre classification","display_name":"Supervised dictionary learning for music genre classification","publication_year":2012,"publication_date":"2012-06-05","ids":{"openalex":"https://openalex.org/W1980599288","doi":"https://doi.org/10.1145/2324796.2324859","mag":"1980599288"},"language":"en","primary_location":{"id":"doi:10.1145/2324796.2324859","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2324796.2324859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Conference on Multimedia Retrieval","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/A5011045620","display_name":"Chin\u2010Chia Michael Yeh","orcid":"https://orcid.org/0000-0002-9807-2963"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]},{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chin-Chia Michael Yeh","raw_affiliation_strings":["Research Center for IT Innovation Academia Sinica, Taipei, Taiwan","[Research Center for IT innovation, Academia Sinica, Taipei, Taiwan]"],"affiliations":[{"raw_affiliation_string":"Research Center for IT Innovation Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"[Research Center for IT innovation, Academia Sinica, Taipei, Taiwan]","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]},{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Research Center for IT Innovation Academia Sinica, Taipei, Taiwan","[Research Center for IT innovation, Academia Sinica, Taipei, Taiwan]"],"affiliations":[{"raw_affiliation_string":"Research Center for IT Innovation Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210086894"]},{"raw_affiliation_string":"[Research Center for IT innovation, Academia Sinica, Taipei, Taiwan]","institution_ids":["https://openalex.org/I84653119"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011045620"],"corresponding_institution_ids":["https://openalex.org/I4210086894","https://openalex.org/I84653119"],"apc_list":null,"apc_paid":null,"fwci":4.7068,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.96531682,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9943000078201294,"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":0.9904000163078308,"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/codebook","display_name":"Codebook","score":0.921132504940033},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7260624766349792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6466764211654663},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6379711627960205},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6367012858390808},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5978012084960938},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5847744345664978},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5792112350463867},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5616323351860046},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4759873151779175},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.4165312349796295},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.381736695766449},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34818941354751587}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.921132504940033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7260624766349792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6466764211654663},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6379711627960205},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6367012858390808},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5978012084960938},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5847744345664978},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5792112350463867},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5616323351860046},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4759873151779175},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.4165312349796295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.381736695766449},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34818941354751587},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2324796.2324859","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2324796.2324859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G4175918646","display_name":null,"funder_award_id":"NSC 100-2218-E-001-009","funder_id":"https://openalex.org/F4320321040","funder_display_name":"National Science Council"}],"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":61,"referenced_works":["https://openalex.org/W625810977","https://openalex.org/W1501755821","https://openalex.org/W1539012881","https://openalex.org/W1562529351","https://openalex.org/W1915070853","https://openalex.org/W1986931325","https://openalex.org/W1988657342","https://openalex.org/W1989445502","https://openalex.org/W2005876975","https://openalex.org/W2008133390","https://openalex.org/W2021659075","https://openalex.org/W2036718463","https://openalex.org/W2038678505","https://openalex.org/W2055356414","https://openalex.org/W2063978378","https://openalex.org/W2069959554","https://openalex.org/W2078120539","https://openalex.org/W2097018403","https://openalex.org/W2099760476","https://openalex.org/W2101252291","https://openalex.org/W2104352833","https://openalex.org/W2105892554","https://openalex.org/W2107430826","https://openalex.org/W2113262625","https://openalex.org/W2119577488","https://openalex.org/W2126863010","https://openalex.org/W2127566601","https://openalex.org/W2129638017","https://openalex.org/W2133824856","https://openalex.org/W2133999183","https://openalex.org/W2134380836","https://openalex.org/W2135046866","https://openalex.org/W2136922672","https://openalex.org/W2138286601","https://openalex.org/W2138635707","https://openalex.org/W2141520175","https://openalex.org/W2142838865","https://openalex.org/W2144383041","https://openalex.org/W2146078527","https://openalex.org/W2148748626","https://openalex.org/W2151103935","https://openalex.org/W2151816810","https://openalex.org/W2158149960","https://openalex.org/W2163759924","https://openalex.org/W2167969117","https://openalex.org/W2179325748","https://openalex.org/W2188492526","https://openalex.org/W2290845176","https://openalex.org/W2293772821","https://openalex.org/W2295991281","https://openalex.org/W2296587773","https://openalex.org/W2395291588","https://openalex.org/W2396521656","https://openalex.org/W2399467590","https://openalex.org/W2399961058","https://openalex.org/W2406196141","https://openalex.org/W2949186849","https://openalex.org/W3023786531","https://openalex.org/W6632282575","https://openalex.org/W6711773680","https://openalex.org/W6711973445"],"related_works":["https://openalex.org/W2293149949","https://openalex.org/W2026099691","https://openalex.org/W4284672201","https://openalex.org/W2377486419","https://openalex.org/W2943202426","https://openalex.org/W2137816434","https://openalex.org/W2163679795","https://openalex.org/W2736714427","https://openalex.org/W2017956276","https://openalex.org/W2012023010"],"abstract_inverted_index":{"This":[0],"paper":[1],"concerns":[2],"the":[3,27,55,62,79,92,99,104,117,121],"development":[4],"of":[5,32,39,61,81,111],"a":[6,19,37,47],"music":[7,112],"codebook":[8,41],"for":[9,128],"summarizing":[10],"local":[11,67,122],"feature":[12,68,123],"descriptors":[13],"computed":[14],"over":[15,85],"time.":[16],"Comparing":[17],"to":[18],"holistic":[20],"representation,":[21],"this":[22],"text-like":[23],"representation":[24],"better":[25],"captures":[26],"rich":[28],"and":[29,44,70,98,132,136],"time-varying":[30],"information":[31],"music.":[33],"We":[34],"systematically":[35],"compare":[36],"number":[38],"existing":[40],"generation":[42],"techniques":[43],"also":[45,74],"propose":[46],"new":[48,93],"one":[49],"that":[50],"incorporates":[51],"labeled":[52],"data":[53],"in":[54],"dictionary":[56,83,95],"learning":[57,84,96],"process.":[58],"Several":[59],"aspects":[60],"encoding":[63,72],"system":[64],"such":[65],"as":[66,120],"extraction":[69],"codeword":[71],"are":[73,134],"analyzed.":[75],"Our":[76],"result":[77],"demonstrates":[78],"superiority":[80],"sparsity-enforced":[82],"conventional":[86],"VQ-based":[87],"or":[88],"exemplar-based":[89],"methods.":[90],"With":[91],"supervised":[94],"algorithm":[97],"optimal":[100],"settings":[101],"inferred":[102],"from":[103],"performance":[105],"study,":[106],"we":[107],"achieve":[108],"state-of-the-art":[109],"accuracy":[110],"genre":[113],"classification":[114,126],"using":[115],"just":[116],"log-power":[118],"spectrogram":[119],"descriptor.":[124],"The":[125],"accuracies":[127],"benchmark":[129],"datasets":[130],"GTZAN":[131],"IS-MIR2004Genre":[133],"84.7%":[135],"90.8%,":[137],"respectively.":[138]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}