{"id":"https://openalex.org/W4403511362","doi":"https://doi.org/10.23919/spa61993.2024.10715611","title":"Automatic re-labeling of Google AudioSet for improved quality of learned features and pre-training","display_name":"Automatic re-labeling of Google AudioSet for improved quality of learned features and pre-training","publication_year":2024,"publication_date":"2024-09-25","ids":{"openalex":"https://openalex.org/W4403511362","doi":"https://doi.org/10.23919/spa61993.2024.10715611"},"language":"en","primary_location":{"id":"doi:10.23919/spa61993.2024.10715611","is_oa":false,"landing_page_url":"https://doi.org/10.23919/spa61993.2024.10715611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01JXZE94BAKQY1SG6EPXYZX4F7/file/01JXZEMHFGJP67BPHTN8ZWK76Y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045397888","display_name":"Tomasz Grzywalski","orcid":"https://orcid.org/0000-0002-9388-0494"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Tomasz Grzywalski","raw_affiliation_strings":["Ghent University,Department of Information Technology,Ghent,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University,Department of Information Technology,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069519911","display_name":"Dick Botteldooren","orcid":"https://orcid.org/0000-0002-7756-7238"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dick Botteldooren","raw_affiliation_strings":["Ghent University,Department of Information Technology,Ghent,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University,Department of Information Technology,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9697999954223633,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9697999954223633,"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/T11309","display_name":"Music and Audio Processing","score":0.9448999762535095,"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":0.9178000092506409,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8239465355873108},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7187731266021729},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6003016233444214},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48982974886894226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45252907276153564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8239465355873108},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7187731266021729},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6003016233444214},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48982974886894226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45252907276153564},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/spa61993.2024.10715611","is_oa":false,"landing_page_url":"https://doi.org/10.23919/spa61993.2024.10715611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01JXZE94BAKQY1SG6EPXYZX4F7","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01JXZE94BAKQY1SG6EPXYZX4F7","pdf_url":"https://biblio.ugent.be/publication/01JXZE94BAKQY1SG6EPXYZX4F7/file/01JXZEMHFGJP67BPHTN8ZWK76Y.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9788362065486","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01JXZE94BAKQY1SG6EPXYZX4F7","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01JXZE94BAKQY1SG6EPXYZX4F7","pdf_url":"https://biblio.ugent.be/publication/01JXZE94BAKQY1SG6EPXYZX4F7/file/01JXZEMHFGJP67BPHTN8ZWK76Y.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9788362065486","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403511362.pdf","grobid_xml":"https://content.openalex.org/works/W4403511362.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2031489346","https://openalex.org/W2593116425","https://openalex.org/W2959241047","https://openalex.org/W3021910945","https://openalex.org/W3082319384","https://openalex.org/W3094550259","https://openalex.org/W3162331882","https://openalex.org/W3196974791","https://openalex.org/W4385823250","https://openalex.org/W4388115392"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"AudioSet,":[0],"comprising":[1],"over":[2],"2":[3],"million":[4],"human-labeled":[5],"sound":[6,64,132],"clips,":[7],"remains":[8],"one":[9,79],"of":[10,34,87,102,123,131,149,184,196,227,233],"the":[11,71,84,88,100,110,147,153,167,185,194,225,231],"biggest":[12],"and":[13,66,95,177],"most":[14,111],"versatile":[15],"publicly":[16],"available":[17],"audio":[18],"events":[19],"datasets.":[20],"Deep":[21],"neural":[22],"networks":[23],"trained":[24,155,199,212],"on":[25,156,181,200],"this":[26,222],"data":[27,234],"are":[28,47,134],"able":[29],"to":[30,62,77,173,230,238],"detect":[31],"527":[32],"types":[33],"sounds":[35],"organized":[36],"in":[37,165,193],"a":[38,57,128,159,218,236],"hierarchical":[39],"(tree-like)":[40],"structure":[41],"named":[42],"ontology.":[43,85],"However,":[44],"these":[45],"models":[46,154,198,211],"also":[48],"often":[49],"used":[50],"as":[51,56,235],"feature":[52],"extractors":[53],"or":[54,80,204],"serve":[55],"basis":[58],"for":[59],"knowledge":[60],"transfer":[61],"other":[63],"detection":[65],"classification":[67],"tasks.":[68],"When":[69],"describing":[70],"AudioSet":[72,215],"recordings,":[73],"raters":[74,92,107],"were":[75,93],"asked":[76],"choose":[78],"more":[81,219],"labels":[82,113,119,138],"from":[83,209],"Analysis":[86],"dataset":[89,168],"reveals":[90],"that":[91],"inconsistent":[94],"imprecise":[96],"when":[97],"dealing":[98],"with":[99,136,206,213],"hierarchy":[101],"sounds.":[103],"For":[104],"example,":[105],"some":[106],"selected":[108,116,124],"only":[109],"precise":[112],"while":[114],"others":[115],"all":[117,121,182],"relevant":[118],"(i.e.":[120],"parents":[122],"child":[125],"labels).":[126],"Additionally,":[127],"large":[129],"fraction":[130],"clips":[133],"labeled":[135],"general":[137,220],"without":[139],"providing":[140],"any":[141],"fine-grained":[142],"labels.":[143],"These":[144],"issues":[145],"harm":[146],"quality":[148],"features":[150,201],"learned":[151],"by":[152],"AudioSet.":[157],"As":[158],"remedy,":[160],"we":[161],"propose":[162],"two":[163],"ways":[164],"which":[166],"can":[169],"be":[170],"automatically":[171],"re-labeled":[172,214],"achieve":[174],"specific,":[175],"consistent":[176],"complete":[178],"label":[179],"definitions":[180],"levels":[183],"ontology":[186],"tree.":[187],"Experimental":[188],"results":[189],"show":[190],"significant":[191],"improvement":[192],"performance":[195],"new":[197],"extracted":[202],"from,":[203],"initialized":[205],"weights":[207],"transferred":[208],"base":[210],"data.":[216],"In":[217],"view,":[221],"work":[223],"highlights":[224],"importance":[226],"paying":[228],"attention":[229],"labeling":[232],"way":[237],"improve":[239],"model":[240],"accuracy.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}