{"id":"https://openalex.org/W4375869216","doi":"https://doi.org/10.1109/icassp49357.2023.10095504","title":"Training Sound Event Detection with Soft Labels from Crowdsourced Annotations","display_name":"Training Sound Event Detection with Soft Labels from Crowdsourced Annotations","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869216","doi":"https://doi.org/10.1109/icassp49357.2023.10095504"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":false,"raw_author_name":"Irene Mart\u00edn-Morat\u00f3","raw_affiliation_strings":["Tampere University,Computing Sciences,Tampere,Finland","Computing Sciences, Tampere University, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Computing Sciences,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Computing Sciences, Tampere University, Tampere, Finland","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":["Tampere University,Computing Sciences,Tampere,Finland","Computing Sciences, Tampere University, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Computing Sciences,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Computing Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031215404","display_name":"Paul Ahokas","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":"Paul Ahokas","raw_affiliation_strings":["Tampere University,Computing Sciences,Tampere,Finland","Computing Sciences, Tampere University, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Computing Sciences,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]},{"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":["Tampere University,Computing Sciences,Tampere,Finland","Computing Sciences, Tampere University, Tampere, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Computing Sciences,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Computing Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8476,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85997276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9993000030517578,"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/T11220","display_name":"Water Systems and Optimization","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.850149393081665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7571506500244141},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7279510498046875},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7074586153030396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5369550585746765},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.532534122467041},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5268644094467163},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4181234836578369},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3906973898410797},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3764585852622986},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35395336151123047},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07809647917747498}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.850149393081665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7571506500244141},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7279510498046875},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7074586153030396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5369550585746765},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.532534122467041},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5268644094467163},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4181234836578369},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3906973898410797},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3764585852622986},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35395336151123047},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07809647917747498},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/206948","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/206948","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321108","display_name":"Academy of Finland","ror":"https://ror.org/05k73zm37"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1503398984","https://openalex.org/W1861492603","https://openalex.org/W2038484192","https://openalex.org/W2108598243","https://openalex.org/W2183341477","https://openalex.org/W2251818274","https://openalex.org/W2566935005","https://openalex.org/W2765407302","https://openalex.org/W2775505379","https://openalex.org/W2903137797","https://openalex.org/W2938440247","https://openalex.org/W2941505948","https://openalex.org/W2963099423","https://openalex.org/W3005295611","https://openalex.org/W3006275583","https://openalex.org/W3015591594","https://openalex.org/W3109837239","https://openalex.org/W3124216180","https://openalex.org/W3125993195","https://openalex.org/W3162331882","https://openalex.org/W3162999565","https://openalex.org/W3183597915","https://openalex.org/W4205977023","https://openalex.org/W4225768055","https://openalex.org/W4285483536","https://openalex.org/W4292513501","https://openalex.org/W4315926819","https://openalex.org/W6691296735","https://openalex.org/W6745136726","https://openalex.org/W6747331233","https://openalex.org/W6756597712","https://openalex.org/W6780411803","https://openalex.org/W6839966804"],"related_works":["https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2025875869","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"study":[4],"the":[5,55,59,62,88,96,99,105,118],"use":[6],"of":[7,38,57,92,98],"soft":[8,69,106,145],"labels":[9,20,47,63,70,107,136],"to":[10,45,111],"train":[11],"a":[12,35,81,127],"system":[13,89],"for":[14,27,52,137],"sound":[15,138],"event":[16],"detection":[17],"(SED).":[18],"Soft":[19],"can":[21,71],"result":[22],"from":[23],"annotations":[24,44],"which":[25,101],"account":[26],"human":[28],"uncertainty":[29],"about":[30,61,95],"categories,":[31],"or":[32],"emerge":[33],"as":[34],"natural":[36],"representation":[37],"multiple":[39],"opinions":[40],"in":[41,49,79,104,117,140],"annotation.":[42],"Converting":[43],"hard":[46,147],"results":[48,85],"unambiguous":[50],"categories":[51],"training,":[53],"at":[54],"cost":[56],"losing":[58],"details":[60],"distribution.":[64],"This":[65],"work":[66],"investigates":[67],"how":[68],"be":[72],"used,":[73],"and":[74,108,146],"what":[75],"benefits":[76],"they":[77],"bring":[78],"training":[80,122],"SED":[82],"system.":[83],"The":[84],"show":[86],"that":[87,114],"is":[90,102,109],"capable":[91],"learning":[93],"information":[94],"activity":[97],"sounds":[100,113],"reflected":[103],"able":[110],"detect":[112],"are":[115],"missed":[116],"typical":[119],"binary":[120],"target":[121],"setup.":[123],"We":[124],"also":[125],"release":[126],"new":[128],"dataset":[129],"produced":[130],"through":[131],"crowdsourcing,":[132],"containing":[133],"temporally":[134],"strong":[135],"events":[139],"real-life":[141],"recordings,":[142],"with":[143],"both":[144],"labels.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}