{"id":"https://openalex.org/W4392904307","doi":"https://doi.org/10.1109/icassp48485.2024.10447675","title":"A Unified Loss Function to Tackle Inter-Class and Intra-Class Data Imbalance in Sound Event Detection","display_name":"A Unified Loss Function to Tackle Inter-Class and Intra-Class Data Imbalance in Sound Event Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904307","doi":"https://doi.org/10.1109/icassp48485.2024.10447675"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100683004","display_name":"Yuliang Zhang","orcid":"https://orcid.org/0000-0003-3249-5629"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuliang Zhang","raw_affiliation_strings":["The University of Western Australia,School of Electrical, Electronic and Computer Engineering","School of Electrical, Electronic and Computer Engineering, The University of Western Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Western Australia,School of Electrical, Electronic and Computer Engineering","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"School of Electrical, Electronic and Computer Engineering, The University of Western Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017213156","display_name":"Roberto Togneri","orcid":"https://orcid.org/0000-0002-3778-4633"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Roberto Togneri","raw_affiliation_strings":["The University of Western Australia,School of Electrical, Electronic and Computer Engineering","School of Electrical, Electronic and Computer Engineering, The University of Western Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Western Australia,School of Electrical, Electronic and Computer Engineering","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"School of Electrical, Electronic and Computer Engineering, The University of Western Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088212422","display_name":"Defeng Huang","orcid":"https://orcid.org/0000-0002-1431-8859"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Huang","raw_affiliation_strings":["The University of Western Australia,School of Electrical, Electronic and Computer Engineering","School of Electrical, Electronic and Computer Engineering, The University of Western Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Western Australia,School of Electrical, Electronic and Computer Engineering","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"School of Electrical, Electronic and Computer Engineering, The University of Western Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5286,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81519953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"996","last_page":"1000"},"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":0.9972000122070312,"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":0.9919999837875366,"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/class","display_name":"Class (philosophy)","score":0.7175151109695435},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6542952656745911},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6247345209121704},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5250817537307739},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.47231221199035645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3562154769897461},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33891189098358154},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07086586952209473}],"concepts":[{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.7175151109695435},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6542952656745911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6247345209121704},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5250817537307739},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.47231221199035645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3562154769897461},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33891189098358154},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07086586952209473},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/183fdd42-6c09-42ab-a8ff-98887ed163cc","is_oa":false,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/183fdd42-6c09-42ab-a8ff-98887ed163cc","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Zhang , Y , Togneri , R & Huang , D 2024 , A UNIFIED LOSS FUNCTION TO TACKLE INTER-CLASS AND INTRA-CLASS DATA IMBALANCE IN SOUND EVENT DETECTION . in ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings , IEEE, Institute of Electrical and Electronics Engineers , pp. 996-1000 , 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, Seoul , Korea, Republic of , 14/04/24 . https://doi.org/10.1109/ICASSP48485.2024.10447675","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W2118230268","https://openalex.org/W2135131618","https://openalex.org/W2408239454","https://openalex.org/W2526050071","https://openalex.org/W2552032035","https://openalex.org/W2566935005","https://openalex.org/W2591013610","https://openalex.org/W2746554716","https://openalex.org/W2758870122","https://openalex.org/W2759976799","https://openalex.org/W2801393360","https://openalex.org/W2883595988","https://openalex.org/W2963351448","https://openalex.org/W2973152780","https://openalex.org/W3016059657","https://openalex.org/W3016195076","https://openalex.org/W4283582457","https://openalex.org/W6747331233"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W4313595395","https://openalex.org/W2312783472","https://openalex.org/W2909748163"],"abstract_inverted_index":{"Data":[0],"imbalance":[1,21,34,44,66,69],"is":[2],"an":[3],"important":[4],"issue":[5],"in":[6],"data-driven":[7],"deep-learning":[8],"methodologies.":[9],"In":[10,50],"sound":[11,30,36,108],"event":[12,37],"detection":[13],"(SED),":[14],"there":[15],"are":[16],"two":[17],"types":[18],"of":[19,29,94],"data":[20,33],"issues":[22],"caused":[23],"by":[24],"the":[25,32,42,46,64,75,97,102],"diverse":[26],"time":[27],"duration":[28],"events:":[31],"between":[35],"classes":[38],"(inter-class":[39],"imbalance)":[40],"and":[41,67,80],"active/inactive":[43],"within":[45],"class":[47],"(intra-class":[48],"imbalance).":[49],"this":[51],"paper,":[52],"we":[53],"propose":[54],"a":[55],"unified":[56],"loss":[57,87,99],"function":[58],"(ULF),":[59],"which":[60],"adeptly":[61],"addresses":[62],"both":[63],"inter-class":[65],"intra-class":[68],"simultaneously.":[70],"Evaluation":[71],"experiments":[72],"substantiate":[73],"that":[74,89],"ULF":[76,98],"consistently":[77],"yields":[78],"superior":[79],"more":[81],"stable":[82],"performance":[83],"compared":[84],"to":[85,105],"existing":[86],"functions":[88],"singularly":[90],"address":[91],"either":[92],"type":[93],"imbalance.":[95],"Furthermore,":[96],"also":[100],"enhances":[101],"model's":[103],"capacity":[104],"detect":[106],"hard-to-detect":[107],"events.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}