{"id":"https://openalex.org/W3211040942","doi":"https://doi.org/10.5281/zenodo.5554753","title":"Improving Generalization of Deep Learning Music Classifiers","display_name":"Improving Generalization of Deep Learning Music Classifiers","publication_year":2021,"publication_date":"2021-09-15","ids":{"openalex":"https://openalex.org/W3211040942","doi":"https://doi.org/10.5281/zenodo.5554753","mag":"3211040942"},"language":"en","primary_location":{"id":"mag:3211040942","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/5554754","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zenodo (CERN European Organization for Nuclear Research)","raw_type":null},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/5554754","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087112013","display_name":"Morgan Buisson","orcid":"https://orcid.org/0000-0001-8541-3071","observed_orcids":["https://orcid.org/0000-0001-8541-3071"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Morgan Buisson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5087112013"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/music-classification","display_name":"music classification","score":0.9810000061988831},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.7820000052452087},{"id":"https://openalex.org/keywords/small-datasets","display_name":"small datasets","score":0.7789999842643738},{"id":"https://openalex.org/keywords/data-sparsity","display_name":"data sparsity","score":0.8690000176429749},{"id":"https://openalex.org/keywords/out-of-distribution-generalization","display_name":"out-of-distribution generalization","score":0.8510000109672546},{"id":"https://openalex.org/keywords/audio-data-augmentation","display_name":"audio data augmentation","score":0.7540000081062317},{"id":"https://openalex.org/keywords/outlier-detection","display_name":"outlier detection","score":0.953000009059906},{"id":"https://openalex.org/keywords/label-smoothing","display_name":"label smoothing","score":0.9750000238418579},{"id":"https://openalex.org/keywords/noisy-labels","display_name":"label noise","score":0.8240000009536743},{"id":"https://openalex.org/keywords/model-robustness","display_name":"model robustness","score":0.8489999771118164},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.9639999866485596},{"id":"https://openalex.org/keywords/perceptual-ambiguity","display_name":"perceptual ambiguity","score":0.6869999766349792},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"music information retrieval","score":0.5799999833106995}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6361531019210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5758859515190125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45442911982536316},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44283580780029297},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4378655254840851},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20448490977287292},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"mag:3211040942","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/5554754","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zenodo (CERN European Organization for Nuclear Research)","raw_type":null},{"id":"doi:10.5281/zenodo.5554753","doi":"https://doi.org/10.5281/zenodo.5554753","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5554753","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"},{"id":"doi:10.5281/zenodo.5554754","doi":"https://doi.org/10.5281/zenodo.5554754","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5554754","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dissertation"}],"best_oa_location":{"id":"mag:3211040942","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/5554754","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zenodo (CERN European Organization for Nuclear Research)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4224918495","https://openalex.org/W2994884786","https://openalex.org/W2621909880","https://openalex.org/W2969426323","https://openalex.org/W3127445407","https://openalex.org/W4414549272","https://openalex.org/W7152655200","https://openalex.org/W3165010842","https://openalex.org/W2946107722","https://openalex.org/W7204439033"],"abstract_inverted_index":{"Deep":[0],"learning":[1,29,32,89,218],"models":[2,33,65,262],"have":[3,172],"recently":[4],"led":[5],"to":[6,53,69,78,82,100,105,122,181,220,231,257,268],"significant":[7],"improvements":[8,259],"in":[9,80,103,173,199,235],"a":[10,18,60,96,174,200,215],"wide":[11],"variety":[12],"of":[13,23,40,46,87,98,110,126,147,150,224,272],"tasks.":[14],"Known":[15],"as":[16],"being":[17],"very":[19,115],"powerful":[20],"tool":[21],"capable":[22],"generalizing":[24,68],"better":[25],"than":[26],"traditional":[27],"machine":[28],"approaches,":[30],"deep":[31,88],"still":[34,51],"heavily":[35],"rely":[36],"on":[37,114,245],"large":[38],"quantities":[39],"annotated":[41],"data.":[42],"As":[43],"the":[44,84,107,124,145,167,183,207,239,270],"field":[45],"music":[47,57,71,90,111,252,274],"information":[48,127],"retrieval":[49],"is":[50],"subject":[52],"data":[54,138],"sparsity,":[55],"automatic":[56,251,273],"classification":[58,152,162,195],"remains":[59],"challenging":[61],"problem":[62,109],"and":[63,135,178,226,263],"numerous":[64],"fail":[66],"at":[67],"out-of-distribution":[70],"col-lections.":[72],"This":[73],"project":[74],"investigates":[75],"possible":[76],"directions":[77],"follow":[79],"order":[81,104],"improve":[83,182],"generalization":[85,108],"capacity":[86],"classifiers.":[91],"More":[92],"specifically,":[93],"we":[94,187,213],"suggest":[95],"set":[97],"guidelines":[99],"be":[101,232],"followed":[102],"address":[106],"classifiers":[112],"trained":[113],"small":[116,130,175],"datasets.":[117],"We":[118,140,164],"first":[119],"propose":[120],"ways":[121,180],"maximize":[123],"amount":[125,146],"extracted":[128],"from":[129],"datasets":[131],"through":[132,154],"outliers":[133],"detection":[134],"e\u00ffcient":[136],"audio":[137],"augmentation.":[139],"then":[141],"show":[142],"that":[143,189,236],"considering":[144],"perceptual":[148],"ambiguity":[149],"each":[151],"task":[153,271],"label":[155,169],"smoothing":[156],"can":[157,171,197],"help":[158],"obtaining":[159],"more":[160,201],"generalizable":[161,202],"bounds.":[163],"also":[165],"highlight":[166],"impact":[168],"noise":[170],"dataset":[176],"setting":[177],"explore":[179],"model\u2019s":[184],"robustness.":[185],"Finally,":[186],"argue":[188],"leveraging":[190],"common":[191],"knowledge":[192],"among":[193],"related":[194],"tasks":[196],"result":[198],"internal":[203],"representation":[204],"learned":[205],"by":[206],"model.":[208],"To":[209],"illustrate":[210],"this":[211],"assumption,":[212],"employ":[214],"simple":[216],"multi-task":[217],"architecture":[219],"jointly":[221],"learn":[222],"pairs":[223],"tasks,":[225],"list":[227],"other":[228],"interesting":[229],"axes":[230],"further":[233],"explored":[234],"direction.":[237],"All":[238],"suggested":[240],"approaches":[241],"are":[242],"exper-imentally":[243],"assessed":[244],"two":[246],"state-of-the-art":[247],"CNN":[248],"architectures":[249],"for":[250],"classification.":[253,275],"They":[254],"all":[255],"lead":[256],"consistent":[258],"over":[260],"baseline":[261],"unveil":[264],"new":[265],"relevant":[266],"questions":[267],"rethink":[269]},"counts_by_year":[],"updated_date":"2026-10-07T09:51:55.459714","created_date":"2021-11-08T00:00:00"}