{"id":"https://openalex.org/W4315926819","doi":"https://doi.org/10.1109/taslp.2022.3233468","title":"Strong Labeling of Sound Events Using Crowdsourced Weak Labels and Annotator Competence Estimation","display_name":"Strong Labeling of Sound Events Using Crowdsourced Weak Labels and Annotator Competence Estimation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4315926819","doi":"https://doi.org/10.1109/taslp.2022.3233468"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3233468","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3233468","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10016759.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10016759.pdf","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"],"raw_orcid":"https://orcid.org/0000-0002-2115-0193","affiliations":[{"raw_affiliation_string":"Computing Sciences, Tampere University, Tampere, Finland","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"],"raw_orcid":"https://orcid.org/0000-0002-6640-9752","affiliations":[{"raw_affiliation_string":"Computing Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041615273"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":6.3325,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97486846,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"902","last_page":"914"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9932000041007996,"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/crowdsourcing","display_name":"Crowdsourcing","score":0.9290245771408081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7918518781661987},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.653684139251709},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6532286405563354},{"id":"https://openalex.org/keywords/competence","display_name":"Competence (human resources)","score":0.4845784902572632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4638161063194275},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41378480195999146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3925633132457733},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3538432717323303},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08947882056236267},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.0836654007434845}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.9290245771408081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918518781661987},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.653684139251709},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6532286405563354},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.4845784902572632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4638161063194275},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41378480195999146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3925633132457733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3538432717323303},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08947882056236267},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0836654007434845},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2022.3233468","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3233468","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10016759.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/208009","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/208009","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2022.3233468","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3233468","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10016759.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"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/W4315926819.pdf","grobid_xml":"https://content.openalex.org/works/W4315926819.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W86738361","https://openalex.org/W1559121794","https://openalex.org/W1565931986","https://openalex.org/W2038484192","https://openalex.org/W2148347694","https://openalex.org/W2408239454","https://openalex.org/W2566935005","https://openalex.org/W2593116425","https://openalex.org/W2758074877","https://openalex.org/W2758358029","https://openalex.org/W2771361008","https://openalex.org/W2774116887","https://openalex.org/W2938440247","https://openalex.org/W2941505948","https://openalex.org/W2959539607","https://openalex.org/W3015190346","https://openalex.org/W3015591594","https://openalex.org/W3015805515","https://openalex.org/W3049446265","https://openalex.org/W3083274258","https://openalex.org/W3094550259","https://openalex.org/W3117314925","https://openalex.org/W3122150008","https://openalex.org/W3124216180","https://openalex.org/W3125993195","https://openalex.org/W3161272933","https://openalex.org/W3162999565","https://openalex.org/W3178592608","https://openalex.org/W3197827948","https://openalex.org/W4205689591","https://openalex.org/W4205977023","https://openalex.org/W4236923591","https://openalex.org/W4393816906","https://openalex.org/W4394027331","https://openalex.org/W6691296735","https://openalex.org/W6747331233","https://openalex.org/W6753583920","https://openalex.org/W6756597712","https://openalex.org/W6780411803","https://openalex.org/W6802880880","https://openalex.org/W6803109234"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W4384486036","https://openalex.org/W135177976","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4318823662","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W3207526114","https://openalex.org/W4286908577"],"abstract_inverted_index":{"Crowdsourcing":[0],"is":[1,25,86,183,192],"a":[2,36,50,68,133],"popular":[3],"tool":[4],"for":[5,21,118,124,146],"collecting":[6],"large":[7],"amounts":[8],"of":[9,16,44,53,75,102,127,157,167,212],"annotated":[10],"data,":[11,148,176],"but":[12,122],"the":[13,17,42,76,83,96,108,138,164,168,172,179,187,195,208],"specific":[14],"format":[15],"strong":[18,60,97,114,203,215],"labels":[19,64,98,191,204],"necessary":[20],"sound":[22,169],"event":[23],"detection":[24],"not":[26,116],"easily":[27],"obtainable":[28],"through":[29,100],"crowdsourcing.":[30],"In":[31],"this":[32],"work,":[33],"we":[34],"propose":[35],"novel":[37],"annotation":[38],"workflow":[39],"that":[40,107],"leverages":[41],"efficiency":[43],"crowdsourcing":[45,213],"weak":[46,63],"labels,":[47,82],"and":[48,58,93,140,160,186],"uses":[49],"high":[51],"number":[52],"annotators":[54],"to":[55,72],"produce":[56],"reliable":[57,81,113,201],"objective":[59],"labels.":[61,216],"The":[62],"are":[65,151],"collected":[66],"in":[67,205],"highly":[69],"redundant":[70],"setup,":[71],"allow":[73],"reconstruction":[74],"temporal":[77],"information.":[78],"To":[79],"obtain":[80],"annotators'":[84,181],"competence":[85,182],"estimated":[87,180],"using":[88],"MACE":[89],"(Multi-Annotator":[90],"Competence":[91],"Estimation)":[92],"incorporated":[94],"into":[95],"estimation":[99],"weighing":[101],"individual":[103],"opinions.":[104],"We":[105],"show":[106],"proposed":[109,196],"method":[110],"produces":[111,200],"consistently":[112],"annotations":[115,143],"only":[117,132],"synthetic":[119,147],"audio":[120,125],"mixtures,":[121],"also":[123],"recordings":[126],"real":[128,175],"everyday":[129],"environments.":[130],"While":[131],"maximum":[134],"80%":[135],"coincidence":[136,188],"with":[137,189,207],"complete":[139],"correct":[141],"reference":[142,190],"was":[144],"obtained":[145],"these":[149],"results":[150],"explained":[152],"by":[153,171],"an":[154],"extended":[155],"study":[156],"how":[158],"polyphony":[159],"SNR":[161],"levels":[162],"affect":[163],"identification":[165],"rate":[166],"events":[170],"annotators.":[173],"On":[174],"even":[177],"though":[178],"significantly":[184],"lower":[185],"under":[193],"69%,":[194],"majority":[197],"opinion":[198],"approach":[199],"aggregated":[202],"comparison":[206],"more":[209],"difficult":[210],"task":[211],"directly":[214]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}