{"id":"https://openalex.org/W4221138324","doi":"https://doi.org/10.1109/icassp43922.2022.9747577","title":"A Benchmark of State-of-the-Art Sound Event Detection Systems Evaluated on Synthetic Soundscapes","display_name":"A Benchmark of State-of-the-Art Sound Event Detection Systems Evaluated on Synthetic Soundscapes","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221138324","doi":"https://doi.org/10.1109/icassp43922.2022.9747577"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747577","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":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2202.01487","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056089196","display_name":"Francesca Ronchini","orcid":"https://orcid.org/0000-0001-6897-1645"},"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":"Francesca Ronchini","raw_affiliation_strings":["Université de Lorraine,CNRS, Inria,Loria, Nancy,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine,CNRS, Inria,Loria, Nancy,France","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]},{"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":["Université de Lorraine,CNRS, Inria,Loria, Nancy,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine,CNRS, Inria,Loria, Nancy,France","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8473,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.72206484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1031","last_page":"1035"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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":0.9914000034332275,"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":0.7673013210296631},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.765711784362793},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7587758302688599},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7131078243255615},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5773361921310425},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5398435592651367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.521980881690979},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5153557658195496},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4851404130458832},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46141159534454346},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.10065692663192749},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08275711536407471},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07714256644248962},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07606527209281921}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673013210296631},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.765711784362793},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7587758302688599},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7131078243255615},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5773361921310425},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5398435592651367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.521980881690979},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5153557658195496},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4851404130458832},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46141159534454346},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.10065692663192749},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08275711536407471},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07714256644248962},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07606527209281921},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747577","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:arXiv.org:2202.01487","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.01487","pdf_url":"https://arxiv.org/pdf/2202.01487","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":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-03554305v2","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-03554305","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":null,"license_id":null,"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/Virtual, Singapore. ⟨10.1109/ICASSP43922.2022.9747577⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2202.01487","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2202.01487","pdf_url":"https://arxiv.org/pdf/2202.01487","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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.5600000023841858}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2408239454","https://openalex.org/W2566935005","https://openalex.org/W2759976799","https://openalex.org/W2771361008","https://openalex.org/W2959539607","https://openalex.org/W3006275583","https://openalex.org/W3015190346","https://openalex.org/W3160845765","https://openalex.org/W3162999565","https://openalex.org/W6753516609","https://openalex.org/W6761988927","https://openalex.org/W6779574021","https://openalex.org/W6780411803","https://openalex.org/W6781130467","https://openalex.org/W6783462664","https://openalex.org/W6784682796","https://openalex.org/W6798264668","https://openalex.org/W6798556726","https://openalex.org/W6802291199"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"This":[0,184],"paper":[1],"proposes":[2],"a":[3,21,195],"benchmark":[4],"of":[5,23,104,119,149,161,166],"submissions":[6,32,60],"to":[7,36,54,63,75,88,92,96,101,115,130,138,141,158,174,193],"Detection":[8,29],"and":[9,13,100],"Classification":[10],"Acoustic":[11],"Scene":[12],"Events":[14],"2021":[15,48],"Challenge":[16,49],"(DCASE)":[17],"Task":[18,50],"4":[19],"representing":[20],"sampling":[22],"the":[24,37,46,79,83,117,147,162,167],"state-of-the-art":[25],"in":[26,113],"Sound":[27],"Event":[28],"task.":[30],"The":[31],"are":[33,61,135,155,182,191],"evaluated":[34],"according":[35],"two":[38],"polyphonic":[39],"sound":[40,106],"detection":[41],"score":[42],"scenarios":[43,80],"proposed":[44,85,112],"for":[45,188],"DCASE":[47],"4,":[51],"which":[52],"allow":[53],"make":[55],"an":[56],"analysis":[57],"on":[58,78,122],"whether":[59],"designed":[62,74],"perform":[64],"fine-grained":[65],"temporal":[66,69,102],"segmentation,":[67,70],"coarse-grained":[68],"or":[71],"have":[72,194],"been":[73],"be":[76],"polyvalent":[77],"proposed.We":[81],"study":[82,116],"solutions":[84],"by":[86],"participants":[87],"analyze":[89],"their":[90],"robustness":[91],"varying":[93],"level":[94],"target":[95,105,140],"non-target":[97,120,142,180],"signal-to-noise":[98,143],"ratio":[99,144],"localization":[103,160],"events.":[107],"A":[108],"last":[109,168],"experiment":[110,169],"is":[111,185],"order":[114],"impact":[118],"events":[121,178,181],"systems":[123,128,172,189],"outputs.":[124],"Results":[125,165],"show":[126],"that":[127,171,190],"adapted":[129],"provide":[131],"coarse":[132],"segmentation":[133],"outputs":[134],"more":[136,156],"robust":[137,157],"different":[139],"and,":[145],"with":[146],"help":[148],"specific":[150],"data":[151],"augmentation":[152],"methods,":[153],"they":[154],"time":[159],"original":[163],"event.":[164],"display":[170],"tend":[173],"spuriously":[175],"predict":[176],"short":[177],"when":[179],"present.":[183],"particularly":[186],"true":[187],"tailored":[192],"fine":[196],"segmentation.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}