{"id":"https://openalex.org/W3183597915","doi":"https://doi.org/10.1109/waspaa52581.2021.9632761","title":"Crowdsourcing Strong Labels for Sound Event Detection","display_name":"Crowdsourcing Strong Labels for Sound Event Detection","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3183597915","doi":"https://doi.org/10.1109/waspaa52581.2021.9632761","mag":"3183597915"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2107.12089","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041615273","display_name":"Irene Mart\u00edn-Morat\u00f3","orcid":"https://orcid.org/0000-0002-2115-0193"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Irene Martin-Morato","raw_affiliation_strings":["Computing Sciences, Tampere University,Tampere,FINLAND,33720"],"affiliations":[{"raw_affiliation_string":"Computing Sciences, Tampere University,Tampere,FINLAND,33720","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030053674","display_name":"Manu Harju","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Manu Harju","raw_affiliation_strings":["Computing Sciences, Tampere University,Tampere,FINLAND,33720"],"affiliations":[{"raw_affiliation_string":"Computing Sciences, Tampere University,Tampere,FINLAND,33720","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Computing Sciences, Tampere University,Tampere,FINLAND,33720","Tampere University"],"affiliations":[{"raw_affiliation_string":"Computing Sciences, Tampere University,Tampere,FINLAND,33720","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041615273"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":0.3086,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53591493,"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":"246","last_page":"250"},"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":0.9991999864578247,"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":0.9937999844551086,"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":0.730492889881134},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.7193160057067871},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.7104594111442566},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6230035424232483},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6102302670478821},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.6030977368354797},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.49670034646987915},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4699818193912506},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4694884419441223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46447622776031494},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.389594167470932},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36340922117233276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.730492889881134},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.7193160057067871},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.7104594111442566},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6230035424232483},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6102302670478821},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.6030977368354797},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.49670034646987915},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4699818193912506},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4694884419441223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46447622776031494},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.389594167470932},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36340922117233276},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2107.12089","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.12089","pdf_url":"https://arxiv.org/pdf/2107.12089","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"mag:3183597915","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2107.12089","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:trepo.tuni.fi:10024/220282","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/220282","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"},{"id":"doi:10.48550/arxiv.2107.12089","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.12089","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.12089","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.12089","pdf_url":"https://arxiv.org/pdf/2107.12089","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2360061192","display_name":"Teaching machines to listen","funder_award_id":"332063","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"},{"id":"https://openalex.org/G4923903852","display_name":null,"funder_award_id":"332063","funder_id":"https://openalex.org/F4320321108","funder_display_name":"Academy of Finland"}],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3183597915.pdf","grobid_xml":"https://content.openalex.org/works/W3183597915.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W86738361","https://openalex.org/W1565931986","https://openalex.org/W2007180964","https://openalex.org/W2038484192","https://openalex.org/W2251818274","https://openalex.org/W2592401976","https://openalex.org/W2593116425","https://openalex.org/W2758074877","https://openalex.org/W2758358029","https://openalex.org/W2771361008","https://openalex.org/W2774116887","https://openalex.org/W2775794021","https://openalex.org/W2903137797","https://openalex.org/W2938440247","https://openalex.org/W2941505948","https://openalex.org/W2959539607","https://openalex.org/W2963099423","https://openalex.org/W2963859210","https://openalex.org/W3015190346","https://openalex.org/W3049446265","https://openalex.org/W3162331882","https://openalex.org/W3162999565","https://openalex.org/W4236923591","https://openalex.org/W6691296735","https://openalex.org/W6756597712"],"related_works":["https://openalex.org/W2809117326","https://openalex.org/W3108321527","https://openalex.org/W2912010834","https://openalex.org/W2912406944","https://openalex.org/W2998070268","https://openalex.org/W3201710136","https://openalex.org/W3146884441","https://openalex.org/W3160315469","https://openalex.org/W3161435013","https://openalex.org/W877541198","https://openalex.org/W2268284457","https://openalex.org/W2807634467","https://openalex.org/W2902557560","https://openalex.org/W2057125274","https://openalex.org/W3046001438","https://openalex.org/W2951882290","https://openalex.org/W2913410650","https://openalex.org/W2893211995","https://openalex.org/W2911546262"],"abstract_inverted_index":{"Strong":[0],"labels":[1,33,62,95],"are":[2,104],"a":[3,28,39,65],"necessity":[4],"for":[5,30],"evaluation":[6],"of":[7,53,59,67,82],"sound":[8,134],"event":[9,102],"detection":[10,135],"methods,":[11],"but":[12],"often":[13],"scarcely":[14],"available":[15],"due":[16],"to":[17,78,125,131],"the":[18,23,43,60,80,83,109,113,132],"high":[19,97],"resources":[20],"required":[21],"by":[22],"annotation":[24,44],"task.":[25],"We":[26],"present":[27],"method":[29,93],"estimating":[31],"strong":[32,69],"using":[34],"crowdsourced":[35],"weak":[36,61],"labels,":[37],"through":[38,86],"process":[40],"that":[41],"divides":[42],"task":[45],"into":[46],"simple":[47],"unit":[48],"tasks.":[49],"Based":[50],"on":[51],"estimations":[52],"annotators'":[54],"competence,":[55],"aggregation":[56],"and":[57,123],"processing":[58],"results":[63],"in":[64,76,119],"set":[66],"objective":[68],"labels.":[70],"The":[71,91],"experiment":[72],"uses":[73],"synthetic":[74],"audio":[75],"order":[77],"verify":[79],"quality":[81],"resulting":[84],"annotations":[85,111],"comparison":[87],"with":[88,96,112],"ground":[89,114],"truth.":[90],"proposed":[92],"produces":[94],"precision,":[98],"though":[99],"not":[100],"all":[101],"instances":[103],"recalled.":[105],"Detection":[106],"metrics":[107],"comparing":[108],"produced":[110],"truth":[115],"show":[116],"80%":[117],"F-score":[118],"1":[120],"s":[121],"segments,":[122],"up":[124],"89.5%":[126],"intersection-based":[127],"F1-score":[128],"calculated":[129],"according":[130],"polyphonic":[133],"score":[136],"metrics.":[137]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
