{"id":"https://openalex.org/W4224920041","doi":"https://doi.org/10.1109/icassp43922.2022.9747556","title":"Threshold Independent Evaluation of Sound Event Detection Scores","display_name":"Threshold Independent Evaluation of Sound Event Detection Scores","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224920041","doi":"https://doi.org/10.1109/icassp43922.2022.9747556"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747556","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-03562763","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055580486","display_name":"Janek Ebbers","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Janek Ebbers","raw_affiliation_strings":["Paderborn University,Department of Communications Engineering,Paderborn,Germany,33098"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderborn University,Department of Communications Engineering,Paderborn,Germany,33098","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Paderborn University,Department of Communications Engineering,Paderborn,Germany,33098"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Paderborn University,Department of Communications Engineering,Paderborn,Germany,33098","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"last","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/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["Universit&#x00E9; de Lorraine,CNRS, Inria,Loria,Nancy,France,F-54000","MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Lorraine,CNRS, Inria,Loria,Nancy,France,F-54000","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]},{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]}],"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":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1021","last_page":"1025"},"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":0.9997000098228455,"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":0.9948999881744385,"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":0.6663356423377991},{"id":"https://openalex.org/keywords/receiver-operating-characteristic","display_name":"Receiver operating characteristic","score":0.6257392168045044},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6145550608634949},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.547060489654541},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46903643012046814},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4559226334095001},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4283669590950012},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35261601209640503},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3467583656311035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32766956090927124},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26077187061309814},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11507430672645569}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6663356423377991},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.6257392168045044},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6145550608634949},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.547060489654541},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46903643012046814},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4559226334095001},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4283669590950012},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35261601209640503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3467583656311035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32766956090927124},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26077187061309814},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11507430672645569},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747556","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03562763v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03562763","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 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapore, Singapore. &#x27E8;10.1109/ICASSP43922.2022.9747556&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03562763v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03562763","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 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapore, Singapore. &#x27E8;10.1109/ICASSP43922.2022.9747556&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1976526581","https://openalex.org/W2101234009","https://openalex.org/W2408239454","https://openalex.org/W2593116425","https://openalex.org/W2758358029","https://openalex.org/W2758870122","https://openalex.org/W2759976799","https://openalex.org/W2798579254","https://openalex.org/W2959539607","https://openalex.org/W3015190346","https://openalex.org/W3016195076","https://openalex.org/W3109837239","https://openalex.org/W3160845765","https://openalex.org/W3162176995","https://openalex.org/W3178592608","https://openalex.org/W3197827948","https://openalex.org/W3204067194","https://openalex.org/W4205689591","https://openalex.org/W4323446909","https://openalex.org/W6675354045","https://openalex.org/W6750883802","https://openalex.org/W6780411803","https://openalex.org/W6783462664"],"related_works":["https://openalex.org/W4385649027","https://openalex.org/W4400094315","https://openalex.org/W2348909947","https://openalex.org/W4292672442","https://openalex.org/W2970784617","https://openalex.org/W2362101859","https://openalex.org/W2126639667","https://openalex.org/W2217963778","https://openalex.org/W2791431590","https://openalex.org/W2941610985"],"abstract_inverted_index":{"Performing":[0],"an":[1,36,43,121],"adequate":[2],"evaluation":[3,44,122,172],"of":[4,42,45,64,87,91,134,141,160],"sound":[5,25],"event":[6],"detection":[7,26],"(SED)":[8],"systems":[9,47],"is":[10,15,49,70,79,166],"far":[11],"from":[12,51],"trivial":[13],"and":[14,31,137,144],"still":[16],"subject":[17],"to":[18,58,151],"ongoing":[19],"research.":[20],"The":[21,89],"recently":[22],"proposed":[23],"polyphonic":[24],"(PSD)-receiver":[27],"operating":[28],"characteristic":[29],"(ROC)":[30],"PSD":[32],"score":[33],"(PSDS)":[34],"make":[35],"important":[37],"step":[38],"into":[39],"the":[40,65,77,92,104,135,153,158],"direction":[41],"SED":[46,171],"which":[48,69,114,155],"independent":[50],"a":[52,60,84,100,112,161],"certain":[53],"decision":[54],"threshold.":[55],"This":[56],"allows":[57,115,150],"obtain":[59],"more":[61],"complete":[62],"picture":[63],"overall":[66],"system":[67,118],"behavior":[68],"less":[71],"biased":[72],"by":[73],"threshold":[74,154],"tuning.":[75],"Yet,":[76],"PSD-ROC":[78,136],"currently":[80],"only":[81,133],"approximated":[82],"using":[83],"finite":[85],"set":[86,123],"thresholds.":[88],"choice":[90],"thresholds":[93,127],"used":[94],"in":[95,169],"approximation,":[96],"however,":[97],"can":[98],"have":[99],"severe":[101],"impact":[102],"on":[103,120],"resulting":[105],"PSDS.":[106],"In":[107],"this":[108],"paper":[109],"we":[110],"propose":[111],"method":[113],"for":[116,124],"computing":[117],"performance":[119,146],"all":[125],"possible":[126],"jointly,":[128],"enabling":[129],"accurate":[130],"computation":[131],"not":[132],"PSDS":[138],"but":[139],"also":[140],"other":[142],"collar-based":[143],"intersection-based":[145],"curves.":[147],"It":[148],"further":[149],"select":[152],"best":[156],"fulfills":[157],"requirements":[159],"given":[162],"application.":[163],"Source":[164],"code":[165],"publicly":[167],"available":[168],"our":[170],"package":[173],"sed_scores_eval":[174],"<sup":[175],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[176],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[177],".":[178]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":7}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}