{"id":"https://openalex.org/W3094148097","doi":"https://doi.org/10.1109/icassp39728.2021.9414711","title":"Improving Sound Event Detection Metrics: Insights from DCASE 2020","display_name":"Improving Sound Event Detection Metrics: Insights from DCASE 2020","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3094148097","doi":"https://doi.org/10.1109/icassp39728.2021.9414711","mag":"3094148097"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.13648","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013662216","display_name":"Giacomo Ferroni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146043","display_name":"Audio Analytic (United Kingdom)","ror":"https://ror.org/04eanvj85","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210146043"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Giacomo Ferroni","raw_affiliation_strings":["Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB","institution_ids":["https://openalex.org/I4210146043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018442184","display_name":"Nicolas Turpault","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Turpault","raw_affiliation_strings":["Universite de Lorraine,CNRS,Nancy,France,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite de Lorraine,CNRS,Nancy,France,F-54000","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004176880","display_name":"Juan Azcarreta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146043","display_name":"Audio Analytic (United Kingdom)","ror":"https://ror.org/04eanvj85","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210146043"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Juan Azcarreta","raw_affiliation_strings":["Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB","institution_ids":["https://openalex.org/I4210146043"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069259475","display_name":"Francesco Tuveri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146043","display_name":"Audio Analytic (United Kingdom)","ror":"https://ror.org/04eanvj85","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210146043"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Francesco Tuveri","raw_affiliation_strings":["Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB","institution_ids":["https://openalex.org/I4210146043"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Romain Serizel","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["Universite de Lorraine,CNRS,Nancy,France,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite de Lorraine,CNRS,Nancy,France,F-54000","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020934947","display_name":"\u00c7a\u011fda\u015f Bilen","orcid":"https://orcid.org/0000-0002-2176-2720"},"institutions":[{"id":"https://openalex.org/I4210146043","display_name":"Audio Analytic (United Kingdom)","ror":"https://ror.org/04eanvj85","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210146043"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cagdas Bilen","raw_affiliation_strings":["Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB","institution_ids":["https://openalex.org/I4210146043"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012719765","display_name":"Sacha Krstulovi\u0107","orcid":"https://orcid.org/0000-0003-4015-4445"},"institutions":[{"id":"https://openalex.org/I4210146043","display_name":"Audio Analytic (United Kingdom)","ror":"https://ror.org/04eanvj85","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210146043"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sacha Krstulovic","raw_affiliation_strings":["Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB","institution_ids":["https://openalex.org/I4210146043"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"631","last_page":"635"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.6831802725791931},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6090283393859863},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5267257690429688},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.48952898383140564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3956017792224884},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3890082836151123},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3670303225517273},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33455610275268555}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6831802725791931},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6090283393859863},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5267257690429688},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.48952898383140564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3956017792224884},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3890082836151123},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3670303225517273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33455610275268555},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.13648","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.13648","pdf_url":"https://arxiv.org/pdf/2010.13648","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":"text"},{"id":"mag:3094148097","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.13648.pdf","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:HAL:hal-02978422v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02978422","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"ICASSP 2021 - 46th International Conference on Acoustics, Speech, and Signal Processing, Jun 2021, Toronto/Virtual, Canada. ⟨10.1109/ICASSP39728.2021.9414711⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2010.13648","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.13648","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":"Preprint"},{"id":"doi:10.17023/0t5k-e425","is_oa":true,"landing_page_url":"https://doi.org/10.17023/0t5k-e425","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.13648","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.13648","pdf_url":"https://arxiv.org/pdf/2010.13648","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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5611049820","display_name":"Learning to understand audio scenes","funder_award_id":"ANR-18-CE23-0020","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1837649128","https://openalex.org/W2116894522","https://openalex.org/W2123843894","https://openalex.org/W2135342008","https://openalex.org/W2169138660","https://openalex.org/W2408239454","https://openalex.org/W2517876061","https://openalex.org/W2758870122","https://openalex.org/W2759976799","https://openalex.org/W2798350598","https://openalex.org/W2884011836","https://openalex.org/W2890573771","https://openalex.org/W2943408595","https://openalex.org/W2959539607","https://openalex.org/W3006275583","https://openalex.org/W3015190346","https://openalex.org/W3084029229","https://openalex.org/W3109837239","https://openalex.org/W6639003370","https://openalex.org/W6750169387","https://openalex.org/W6753516609","https://openalex.org/W6754359508","https://openalex.org/W6761988927","https://openalex.org/W6780411803","https://openalex.org/W6781130467"],"related_works":["https://openalex.org/W2980861325","https://openalex.org/W2364319444","https://openalex.org/W2165271456","https://openalex.org/W2052039741","https://openalex.org/W1529285077","https://openalex.org/W2922013626","https://openalex.org/W2774926692","https://openalex.org/W2894048303","https://openalex.org/W2968966429","https://openalex.org/W3088203140","https://openalex.org/W3208808915","https://openalex.org/W2960842292","https://openalex.org/W2986121528","https://openalex.org/W2909518190","https://openalex.org/W2755093765","https://openalex.org/W2951498981","https://openalex.org/W1583314457","https://openalex.org/W2386994790","https://openalex.org/W2076117539","https://openalex.org/W2264757910"],"abstract_inverted_index":{"The":[0],"ranking":[1],"of":[2,21,45,72,95,112,120],"sound":[3,74,99,125],"event":[4,100,126],"detection":[5],"(SED)":[6],"systems":[7,46,122],"may":[8,81],"be":[9,85],"biased":[10],"by":[11,56,108,123],"assumptions":[12],"inherent":[13],"to":[14,18,105],"evaluation":[15,97],"criteria":[16,32],"and":[17,30,76,84,102],"the":[19,34,60,70,73,78,93,96,118,131],"choice":[20],"an":[22],"operating":[23,133],"point.":[24],"This":[25],"paper":[26],"compares":[27],"conventional":[28,61],"event-based":[29,62],"segment-based":[31,79],"against":[33],"Polyphonic":[35],"Sound":[36],"Detection":[37],"Score":[38],"(PSDS)'s":[39],"intersection-based":[40,90],"criterion,":[41],"over":[42],"a":[43],"selection":[44],"from":[47,130],"DCASE":[48],"2020":[49],"Challenge":[50],"Task":[51],"4.":[52],"It":[53],"shows":[54],"that,":[55],"relying":[57],"on":[58,69,98],"collars,":[59],"criterion":[63,80,91],"introduces":[64],"different":[65],"strictness":[66],"levels":[67],"depending":[68],"length":[71],"events,":[75],"that":[77],"lack":[82],"precision":[83],"application":[86],"dependent.":[87],"Alternatively,":[88],"PSDS's":[89],"overcomes":[92],"dependency":[94],"duration":[101],"provides":[103],"robustness":[104],"labelling":[106],"subjectivity,":[107],"allowing":[109],"valid":[110],"detections":[111],"interrupted":[113],"events.":[114],"Furthermore,":[115],"PSDS":[116],"enhances":[117],"comparison":[119],"SED":[121],"measuring":[124],"modelling":[127],"performance":[128],"independently":[129],"systems'":[132],"points.":[134]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}