{"id":"https://openalex.org/W3044910811","doi":"https://doi.org/10.1109/iwssip48289.2020.9145192","title":"Improving Musical Tag Annotation with Stacking and Convolutional Neural Networks","display_name":"Improving Musical Tag Annotation with Stacking and Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3044910811","doi":"https://doi.org/10.1109/iwssip48289.2020.9145192","mag":"3044910811"},"language":"en","primary_location":{"id":"doi:10.1109/iwssip48289.2020.9145192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwssip48289.2020.9145192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Systems, Signals and Image Processing (IWSSIP)","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/A5081568241","display_name":"Juliano Donini da Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I123443094","display_name":"Universidade Estadual de Maring\u00e1","ror":"https://ror.org/04bqqa360","country_code":"BR","type":"education","lineage":["https://openalex.org/I123443094"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Juliano Donini da Silva","raw_affiliation_strings":["State University of Maringá (UEM),Department of Informatics (DIN),Maringá,PR,Brazil","State University of Maring\u00e1 (UEM), Maring\u00e1, PR, Brazil"],"affiliations":[{"raw_affiliation_string":"State University of Maringá (UEM),Department of Informatics (DIN),Maringá,PR,Brazil","institution_ids":["https://openalex.org/I123443094"]},{"raw_affiliation_string":"State University of Maring\u00e1 (UEM), Maring\u00e1, PR, Brazil","institution_ids":["https://openalex.org/I123443094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114210611","display_name":"Yandre M. G. Da Costa","orcid":null},"institutions":[{"id":"https://openalex.org/I123443094","display_name":"Universidade Estadual de Maring\u00e1","ror":"https://ror.org/04bqqa360","country_code":"BR","type":"education","lineage":["https://openalex.org/I123443094"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Yandre Maldonado Gomes da Costa","raw_affiliation_strings":["State University of Maringá (UEM),Department of Informatics (DIN),Maringá,PR,Brazil","State University of Maring\u00e1 (UEM), Maring\u00e1, PR, Brazil"],"affiliations":[{"raw_affiliation_string":"State University of Maringá (UEM),Department of Informatics (DIN),Maringá,PR,Brazil","institution_ids":["https://openalex.org/I123443094"]},{"raw_affiliation_string":"State University of Maring\u00e1 (UEM), Maring\u00e1, PR, Brazil","institution_ids":["https://openalex.org/I123443094"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069237044","display_name":"Marcos Aur\u00e9lio Domingues","orcid":"https://orcid.org/0000-0001-7195-0714"},"institutions":[{"id":"https://openalex.org/I123443094","display_name":"Universidade Estadual de Maring\u00e1","ror":"https://ror.org/04bqqa360","country_code":"BR","type":"education","lineage":["https://openalex.org/I123443094"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos Aur\u00e9lio Domingues","raw_affiliation_strings":["State University of Maringá (UEM),Department of Informatics (DIN),Maringá,PR,Brazil","State University of Maring\u00e1 (UEM), Maring\u00e1, PR, Brazil"],"affiliations":[{"raw_affiliation_string":"State University of Maringá (UEM),Department of Informatics (DIN),Maringá,PR,Brazil","institution_ids":["https://openalex.org/I123443094"]},{"raw_affiliation_string":"State University of Maring\u00e1 (UEM), Maring\u00e1, PR, Brazil","institution_ids":["https://openalex.org/I123443094"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081568241"],"corresponding_institution_ids":["https://openalex.org/I123443094"],"apc_list":null,"apc_paid":null,"fwci":0.1524,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42823499,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"393","last_page":"398"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9714999794960022,"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":0.849596381187439},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.813386082649231},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7676886320114136},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7389237880706787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5981038212776184},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5859487056732178},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4924801290035248},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3889353275299072},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3785959482192993},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3646494150161743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3382463753223419}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.849596381187439},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.813386082649231},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7676886320114136},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7389237880706787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5981038212776184},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5859487056732178},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4924801290035248},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3889353275299072},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3785959482192993},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3646494150161743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3382463753223419},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwssip48289.2020.9145192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwssip48289.2020.9145192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Systems, Signals and Image Processing (IWSSIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W55768394","https://openalex.org/W2059652044","https://openalex.org/W2108672713","https://openalex.org/W2132221437","https://openalex.org/W2133233905","https://openalex.org/W2145378985","https://openalex.org/W2155653793","https://openalex.org/W2406403389","https://openalex.org/W2407683213","https://openalex.org/W2414894569","https://openalex.org/W2563031223","https://openalex.org/W2580221632","https://openalex.org/W2736887001","https://openalex.org/W2767858146","https://openalex.org/W2929033724","https://openalex.org/W6679847170","https://openalex.org/W6713900508","https://openalex.org/W6714262827"],"related_works":["https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3167935049","https://openalex.org/W3103566983","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Personalized":[0],"music":[1,18,33,77],"systems":[2],"usually":[3],"rely":[4],"on":[5,40],"manual":[6,22],"song":[7,37],"annotations":[8],"(tags)":[9],"as":[10,102,136,170,188],"a":[11,25,44,88],"mechanism":[12],"for":[13],"querying":[14],"and":[15,50,178,212],"navigating":[16],"large":[17,30],"collections.":[19],"However,":[20],"the":[21,29,63,83,92,95,105,124,128,131,139,143,148,152,158,167,173,179,183,191,208],"annotation":[23,38,79],"is":[24,43,100],"hard":[26],"task":[27],"given":[28],"amount":[31],"of":[32,87,94,98,116,122,134,172],"available":[34],"nowadays.":[35],"Automatic":[36],"based":[39],"content":[41],"analysis":[42],"potential":[45],"solution":[46],"to":[47,61,67,75,161],"this":[48,57],"problem":[49],"has":[51],"recently":[52],"been":[53],"gaining":[54],"attention.":[55],"In":[56,81,108,142],"work,":[58],"we":[59,111,146],"propose":[60],"extend":[62],"Stacking":[64],"prediction":[65,85],"framework":[66],"use":[68,147],"Convolutional":[69],"Neural":[70],"Networks":[71],"(CNNs)":[72],"in":[73,90,104,130,138,157,182,190,203,207],"order":[74],"improve":[76],"tag":[78],"task.":[80],"general,":[82],"Stacked":[84],"consists":[86,121],"technique":[89,150],"which":[91],"output":[93],"first":[96,119,132,159,174,184],"stage":[97,133,160,185],"learning":[99],"used":[101,169,187],"input":[103,137,171,189],"second":[106,140,144,192],"stage.":[107,141,175,193],"our":[109,196],"work":[110],"have":[112],"tried":[113],"two":[114],"proposals":[115,197],"extension.":[117],"The":[118,176],"one":[120],"using":[123],"weights":[125,153,177],"learned":[126,154],"by":[127,155],"CNN":[129,156,201],"training":[135],"proposal,":[145],"autoencoder":[149],"with":[151,198],"generate":[162],"images":[163,180],"50%":[164],"smaller":[165],"than":[166],"ones":[168],"obtained":[181],"are":[186],"We":[194],"evaluated":[195],"five":[199],"different":[200],"models":[202],"three":[204],"datasets":[205],"well-known":[206],"literature":[209],"(FMA,":[210],"MillionSong,":[211],"MagnaTagATune),":[213],"obtaining":[214],"interesting":[215],"results.":[216]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}