{"id":"https://openalex.org/W2980861325","doi":"https://doi.org/10.1109/icassp40776.2020.9052995","title":"A Framework for the Robust Evaluation of Sound Event Detection","display_name":"A Framework for the Robust Evaluation of Sound Event Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2980861325","doi":"https://doi.org/10.1109/icassp40776.2020.9052995","mag":"2980861325"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9052995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/1910.08440","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Cagdas Bilen","raw_affiliation_strings":["Audio Analytic - AA Labs, Cambridge, UK","Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB"],"affiliations":[{"raw_affiliation_string":"Audio Analytic - AA Labs, Cambridge, UK","institution_ids":["https://openalex.org/I4210146043"]},{"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/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","Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB"],"affiliations":[{"raw_affiliation_string":"Audio Analytic - AA Labs, Cambridge, UK","institution_ids":["https://openalex.org/I4210146043"]},{"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","Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB"],"affiliations":[{"raw_affiliation_string":"Audio Analytic - AA Labs, Cambridge, UK","institution_ids":["https://openalex.org/I4210146043"]},{"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/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","Audio Analytic - AA Labs,Cambridge,UK,CB5 8AB"],"affiliations":[{"raw_affiliation_string":"Audio Analytic - AA Labs, Cambridge, UK","institution_ids":["https://openalex.org/I4210146043"]},{"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","[Audio Analytic - AA Labs, Cambridge, UK]"],"affiliations":[{"raw_affiliation_string":"Audio Analytic - AA Labs, Cambridge, UK","institution_ids":["https://openalex.org/I4210146043"]},{"raw_affiliation_string":"[Audio Analytic - AA Labs, Cambridge, UK]","institution_ids":["https://openalex.org/I4210146043"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5020934947"],"corresponding_institution_ids":["https://openalex.org/I4210146043"],"apc_list":null,"apc_paid":null,"fwci":1.2182,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.78377848,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"65"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9944999814033508,"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/polyphony","display_name":"Polyphony","score":0.8395572900772095},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7301948070526123},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7172247171401978},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5664073824882507},{"id":"https://openalex.org/keywords/receiver-operating-characteristic","display_name":"Receiver operating characteristic","score":0.5190780162811279},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4742005467414856},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.41991090774536133},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41306763887405396},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40519726276397705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4051269292831421},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12248355150222778},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09680187702178955}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8395572900772095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301948070526123},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7172247171401978},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5664073824882507},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.5190780162811279},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4742005467414856},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.41991090774536133},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41306763887405396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40519726276397705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4051269292831421},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12248355150222778},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09680187702178955},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9052995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.08440","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.08440","pdf_url":"https://arxiv.org/pdf/1910.08440","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:2980861325","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.08440.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":"doi:10.48550/arxiv.1910.08440","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.08440","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"},{"id":"doi:10.17023/n53e-py94","is_oa":true,"landing_page_url":"https://doi.org/10.17023/n53e-py94","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.08440","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.08440","pdf_url":"https://arxiv.org/pdf/1910.08440","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2980861325.pdf","grobid_xml":"https://content.openalex.org/works/W2980861325.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1481604723","https://openalex.org/W1586405805","https://openalex.org/W1837649128","https://openalex.org/W1976526581","https://openalex.org/W2038262612","https://openalex.org/W2078622638","https://openalex.org/W2086384421","https://openalex.org/W2408239454","https://openalex.org/W2442329935","https://openalex.org/W2758870122","https://openalex.org/W2775505379","https://openalex.org/W2775794021","https://openalex.org/W2890573771","https://openalex.org/W2929983093","https://openalex.org/W2982468701","https://openalex.org/W2997266872","https://openalex.org/W6639003370","https://openalex.org/W6718561954","https://openalex.org/W6747331233","https://openalex.org/W6753516609","https://openalex.org/W6754359508","https://openalex.org/W6761152316"],"related_works":["https://openalex.org/W3094148097","https://openalex.org/W2922013626","https://openalex.org/W2924984704","https://openalex.org/W3161168558","https://openalex.org/W3084362207","https://openalex.org/W2738991112","https://openalex.org/W3208808915","https://openalex.org/W3128397507","https://openalex.org/W2165271456","https://openalex.org/W2154259122","https://openalex.org/W2801670977","https://openalex.org/W2909518190","https://openalex.org/W3033521478","https://openalex.org/W1583314457","https://openalex.org/W2755093765","https://openalex.org/W2943730282","https://openalex.org/W3203461458","https://openalex.org/W2932982107","https://openalex.org/W2546201933","https://openalex.org/W3119618471"],"abstract_inverted_index":{"This":[0],"work":[1],"defines":[2],"a":[3,36,70,76,120],"new":[4],"framework":[5,34],"for":[6],"performance":[7,65],"evaluation":[8],"of":[9,20,38,72,122,128,140],"polyphonic":[10,52,78],"sound":[11,79,106],"event":[12,24,26,29,39],"detection":[13,40,80],"(SED)":[14],"systems,":[15],"which":[16,83],"overcomes":[17],"the":[18,21,129,136,141],"limitations":[19],"conventional":[22],"collar-based":[23],"decisions,":[25],"F-scores":[27],"and":[28,68,102,138],"error":[30],"rates.":[31],"The":[32,92,126],"proposed":[33,130],"introduces":[35],"definition":[37],"that":[41],"is":[42],"more":[43,60],"robust":[44],"against":[45],"labelling":[46],"subjectivity.":[47],"It":[48],"also":[49,95],"resorts":[50],"to":[51,58,113,118],"receiver":[53],"operating":[54,89],"characteristic":[55],"(ROC)":[56],"curves":[57,74],"deliver":[59],"global":[61],"insight":[62,98],"into":[63,75,99],"system":[64,85],"than":[66],"F1-scores,":[67],"proposes":[69],"reduction":[71],"these":[73],"single":[77],"score":[81],"(PSDS),":[82],"allows":[84],"comparison":[86],"independently":[87],"from":[88,144],"points":[90],"(OPs).":[91],"presented":[93],"method":[94],"delivers":[96],"better":[97],"data":[100],"biases":[101],"classification":[103],"stability":[104],"across":[105],"classes.":[107],"Furthermore,":[108],"it":[109],"can":[110],"be":[111],"tuned":[112],"varying":[114],"applications":[115],"in":[116],"order":[117],"match":[119],"variety":[121],"user":[123],"experience":[124],"requirements.":[125],"benefits":[127],"approach":[131],"are":[132],"demonstrated":[133],"by":[134],"re-evaluating":[135],"baseline":[137],"two":[139],"top-performing":[142],"systems":[143],"DCASE":[145],"2019":[146],"Task":[147],"4.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}