{"id":"https://openalex.org/W4225313599","doi":"https://doi.org/10.1109/icassp43922.2022.9747736","title":"Time-Balanced Focal Loss for Audio Event Detection","display_name":"Time-Balanced Focal Loss for Audio Event Detection","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225313599","doi":"https://doi.org/10.1109/icassp43922.2022.9747736"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747736","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":"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/A5100750094","display_name":"Sangwook Park","orcid":"https://orcid.org/0000-0002-6817-4846"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sangwook Park","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038788686","display_name":"Mounya Elhilali","orcid":"https://orcid.org/0000-0003-2597-738X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mounya Elhilali","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6052,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.63833805,"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":"311","last_page":"315"},"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":0.9987999796867371,"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":0.9975000023841858,"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/leverage","display_name":"Leverage (statistics)","score":0.7724415063858032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6783629655838013},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5682759284973145},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5437080264091492},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4922255575656891},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4250968396663666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.403278112411499},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38799554109573364},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08889269828796387}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7724415063858032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783629655838013},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5682759284973145},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5437080264091492},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4922255575656891},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4250968396663666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.403278112411499},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38799554109573364},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08889269828796387},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747736","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1650531274","https://openalex.org/W2719034351","https://openalex.org/W2771361008","https://openalex.org/W2884561390","https://openalex.org/W2936503027","https://openalex.org/W2950746339","https://openalex.org/W2959539607","https://openalex.org/W2963691377","https://openalex.org/W3006275583","https://openalex.org/W3109837239","https://openalex.org/W4248066070","https://openalex.org/W6636898527","https://openalex.org/W6731965104","https://openalex.org/W6740574266","https://openalex.org/W6780411803"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W1549289070","https://openalex.org/W2923284750","https://openalex.org/W2893763841","https://openalex.org/W2368779261","https://openalex.org/W1531742702","https://openalex.org/W2936207217","https://openalex.org/W4320165504","https://openalex.org/W3101879006","https://openalex.org/W2517598410"],"abstract_inverted_index":{"Sound":[0],"Event":[1],"Detection":[2],"(SED)":[3],"tackles":[4],"the":[5,77,85,94,110,162,173,177],"challenge":[6,72],"of":[7,39,56,79,88,112,129,164,179],"identifying":[8],"sound":[9,24,51,181],"events":[10,102,107,117],"in":[11,29,61,68,76,97,124,161,176],"an":[12,125],"audio":[13],"recording":[14],"by":[15],"delimiting":[16],"both":[17],"their":[18,62],"temporal":[19],"boundaries":[20],"as":[21,23,64,66,109,119],"well":[22,65],"category.":[25],"With":[26],"recent":[27],"advances":[28],"deep":[30],"learning,":[31],"current":[32],"systems":[33],"are":[34],"able":[35],"to":[36,42,114,159],"leverage":[37],"availability":[38],"large":[40],"datasets":[41],"train":[43],"sophisticated":[44],"and":[45,53,167],"highly":[46],"effective":[47,130],"SED":[48,80,160],"models.":[49],"Nonetheless,":[50],"sources":[52],"acoustic":[54],"characteristics":[55],"different":[57,101],"classes":[58,91],"vary":[59],"greatly":[60],"prevalence":[63],"representation":[67,86,128],"labeled":[69],"datasets.":[70],"The":[71,154],"with":[73],"data":[74],"imbalance":[75,137],"case":[78,178],"stems":[81],"not":[82],"only":[83],"from":[84,104],"(number":[87],"samples)":[89],"across":[90,100],"but":[92],"also":[93],"natural":[95],"asymmetry":[96],"time":[98],"duration":[99],"varying":[103],"short":[105],"transient":[106],"such":[108,118],"clacking":[111],"dishes":[113],"more":[115],"sustained":[116],"vacuuming.":[120],"This":[121],"variability":[122],"results":[123],"inherent":[126],"disproportional":[127],"training":[131],"samples.":[132],"To":[133],"address":[134],"this":[135,139],"compounded":[136],"issue,":[138],"work":[140],"proposes":[141],"a":[142,149,169],"balanced":[143],"focal":[144],"learning":[145],"function":[146],"that":[147],"introduces":[148],"novel":[150],"time-sensitive":[151],"classwise":[152],"weight.":[153],"proposed":[155],"loss":[156],"is":[157],"applied":[158],"context":[163],"DCASE2021":[165],"challenge,":[166],"reports":[168],"notable":[170],"improvement":[171],"over":[172],"baseline,":[174],"particularly":[175],"shorter":[180],"events.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}