{"id":"https://openalex.org/W2125040432","doi":"https://doi.org/10.1109/icassp.2012.6288282","title":"Music genre classification using self-taught learning via sparse coding","display_name":"Music genre classification using self-taught learning via sparse coding","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2125040432","doi":"https://doi.org/10.1109/icassp.2012.6288282","mag":"2125040432"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5039443541","display_name":"Konstantin Markov","orcid":"https://orcid.org/0000-0003-1838-4789"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Konstantin Markov","raw_affiliation_strings":["Human Interface Laboratory, University of Aizu, Fukushima, Japan","Human Interface Lab, University of Aizu, Fukushima, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Interface Laboratory, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]},{"raw_affiliation_string":"Human Interface Lab, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067714865","display_name":"Tomoko Matsui","orcid":"https://orcid.org/0000-0003-3201-6106"},"institutions":[{"id":"https://openalex.org/I4210134673","display_name":"The Institute of Statistical Mathematics","ror":"https://ror.org/03jcejr58","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210134673","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoko Matsui","raw_affiliation_strings":["Department of Statistical Modeling, Institute for Statistical Mathematics, Tokyo, Japan","Dep. of Statistical Modeling, Institute of Statistical Mathematics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistical Modeling, Institute for Statistical Mathematics, Tokyo, Japan","institution_ids":["https://openalex.org/I4210134673"]},{"raw_affiliation_string":"Dep. of Statistical Modeling, Institute of Statistical Mathematics, Tokyo, Japan","institution_ids":["https://openalex.org/I4210134673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9815,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89704673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1929","last_page":"1932"},"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":0.9997000098228455,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7279913425445557},{"id":"https://openalex.org/keywords/neural-coding","display_name":"Neural coding","score":0.58870530128479},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5708818435668945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5577399134635925},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5151011347770691},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5087326169013977},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.46257784962654114},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44871172308921814},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4227387309074402},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.41069650650024414},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4025863707065582},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32407116889953613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12133324146270752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279913425445557},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.58870530128479},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5708818435668945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5577399134635925},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5151011347770691},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5087326169013977},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.46257784962654114},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44871172308921814},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4227387309074402},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.41069650650024414},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4025863707065582},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32407116889953613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12133324146270752},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288282","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1483217829","https://openalex.org/W1554104313","https://openalex.org/W1989975849","https://openalex.org/W2038441671","https://openalex.org/W2038678505","https://openalex.org/W2097089247","https://openalex.org/W2105892554","https://openalex.org/W2113606819","https://openalex.org/W2122922389","https://openalex.org/W2133824856","https://openalex.org/W2165698076","https://openalex.org/W2188492526","https://openalex.org/W2293772821","https://openalex.org/W6633146083","https://openalex.org/W6686925444","https://openalex.org/W6696611969"],"related_works":["https://openalex.org/W2890544631","https://openalex.org/W2067062989","https://openalex.org/W4205656132","https://openalex.org/W2111634407","https://openalex.org/W3004790527","https://openalex.org/W2203155458","https://openalex.org/W2783282829","https://openalex.org/W2138494306","https://openalex.org/W2539392819","https://openalex.org/W212310357"],"abstract_inverted_index":{"Availability":[0],"of":[1,4,127,133,149,167],"large":[2],"amounts":[3],"raw":[5],"unlabeled":[6,27,44,61,97,168],"data":[7,28,45,62,74,98,151,169],"has":[8],"sparked":[9],"the":[10,31,39,60,72,86,101,138,143,147],"recent":[11],"surge":[12],"in":[13,38],"semi-supervised":[14],"learning":[15,41,140],"research.":[16],"In":[17,78],"most":[18],"works,":[19],"however,":[20],"it":[21,68],"is":[22,36,57,69,123,152],"assumed":[23],"that":[24,137,157],"labeled":[25,73,150],"and":[26,66,100,112],"come":[29,109],"from":[30,59,110,130],"same":[32],"distribution.":[33],"This":[34],"restriction":[35],"removed":[37],"self-taught":[40,139],"approach":[42],"where":[43],"can":[46,160],"be":[47,161],"different,":[48],"but":[49],"nevertheless":[50],"have":[51],"similar":[52],"structure.":[53],"First,":[54],"a":[55,164],"representation":[56],"learned":[58],"via":[63],"sparse":[64],"coding":[65],"then":[67],"applied":[70],"to":[71],"used":[75],"for":[76,85,103,115,125,163],"classification.":[77],"this":[79,83],"work,":[80],"we":[81],"implemented":[82],"method":[84,141],"music":[87],"genre":[88,122],"classification":[89,144],"task":[90],"using":[91],"two":[92],"different":[93],"databases:":[94],"one":[95,121],"as":[96],"pool":[99],"other":[102],"supervised":[104],"classifier":[105],"training.":[106],"Music":[107],"pieces":[108],"10":[111],"6":[113],"genres":[114],"each":[116],"database":[117],"respectively,":[118],"while":[119],"only":[120],"common":[124],"both":[126],"them.":[128],"Results":[129],"wide":[131,165],"variety":[132],"experimental":[134],"settings":[135],"show":[136],"improves":[142],"rate":[145],"when":[146],"amount":[148],"small":[153],"and,":[154],"more":[155],"interestingly,":[156],"consistent":[158],"improvement":[159],"achieved":[162],"range":[166],"sizes.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}