{"id":"https://openalex.org/W4388820715","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317385","title":"Improving Sound Event Localization and Detection with Class-Dependent Sound Separation for Real-World Scenarios","display_name":"Improving Sound Event Localization and Detection with Class-Dependent Sound Separation for Real-World Scenarios","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820715","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317385"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5112745123","display_name":"Shi Cheng","orcid":"https://orcid.org/0000-0003-1499-0941"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Cheng","raw_affiliation_strings":["University of Science and Technology of China,Hefei,PR China","University of Science and Technology of China, Hefei, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,PR China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, PR China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,Hefei,PR China","University of Science and Technology of China, Hefei, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,PR China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, PR China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434900","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3843-3920"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,PR China","University of Science and Technology of China, Hefei, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,PR China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, PR China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038529708","display_name":"Ya Jiang","orcid":"https://orcid.org/0000-0003-1733-8887"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Jiang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,PR China","University of Science and Technology of China, Hefei, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,PR China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, PR China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005376611","display_name":"Zhaoxu Nian","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoxu Nian","raw_affiliation_strings":["University of Science and Technology of China,Hefei,PR China","University of Science and Technology of China, Hefei, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,PR China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, PR China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064699619","display_name":"Shutong Niu","orcid":"https://orcid.org/0000-0003-0315-1042"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shutong Niu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,PR China","University of Science and Technology of China, Hefei, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,PR China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, PR China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020803502","display_name":"Yu Gao","orcid":"https://orcid.org/0000-0002-2135-7872"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gao","raw_affiliation_strings":["AI Innovation Center, Midea Group (Shanghai) Co., Ltd.,Shanghai,China,201702"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Innovation Center, Midea Group (Shanghai) Co., Ltd.,Shanghai,China,201702","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086363072","display_name":"Wen-Bin Zhang","orcid":"https://orcid.org/0000-0003-4127-7834"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin Zhang","raw_affiliation_strings":["AI Innovation Center, Midea Group (Shanghai) Co., Ltd.,Shanghai,China,201702"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Innovation Center, Midea Group (Shanghai) Co., Ltd.,Shanghai,China,201702","institution_ids":["https://openalex.org/I4210093653"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9238,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75343568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2068","last_page":"2073"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7881335020065308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6729499101638794},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5091161131858826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.406478613615036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36243242025375366},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.06030118465423584}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7881335020065308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6729499101638794},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5091161131858826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.406478613615036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36243242025375366},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.06030118465423584},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1582796148","https://openalex.org/W1844944916","https://openalex.org/W2593116425","https://openalex.org/W2810934215","https://openalex.org/W2952218014","https://openalex.org/W2963812188","https://openalex.org/W2982382207","https://openalex.org/W2982429715","https://openalex.org/W2998139081","https://openalex.org/W3024840775","https://openalex.org/W3083274258","https://openalex.org/W3099330747","https://openalex.org/W3117314925","https://openalex.org/W3163193264","https://openalex.org/W3203177955","https://openalex.org/W3206329344","https://openalex.org/W3217491327","https://openalex.org/W4224919083","https://openalex.org/W4224919399","https://openalex.org/W4282031641","https://openalex.org/W4287120192","https://openalex.org/W4297797459","https://openalex.org/W4308868387","https://openalex.org/W4309092811","https://openalex.org/W4324116353","https://openalex.org/W4372263497","https://openalex.org/W4372270119","https://openalex.org/W6838853441"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"In":[0,93,187],"this":[1],"study,":[2],"we":[3,46,141],"propose":[4],"a":[5,26,68,162],"novel":[6],"approach":[7],"to":[8,21,51,95,165,195,200],"sound":[9,17,33,39,147,159,179],"event":[10,40,70,148,185],"localization":[11],"and":[12,35,56,88,125,151,181],"detection":[13,149],"(SELD)":[14],"by":[15,104],"using":[16],"separation":[18,160],"(SS)":[19],"models":[20,50],"tackle":[22],"key":[23],"challenges":[24],"of":[25,29,38,67,80,117,169,184,203],"high":[27,176],"percentage":[28],"overlapped":[30],"segments":[31],"between":[32,178],"events":[34,180],"imbalanced":[36,182],"distributions":[37,183],"classes":[41],"in":[42,85,90,122,127,145,173],"real-world":[43,91,128],"scenarios.":[44,92,129],"Specifically,":[45],"introduce":[47],"class-dependent":[48,110],"SS":[49,61,111],"deal":[52],"with":[53,175],"overlapping":[54],"mixtures":[55],"extract":[57],"features":[58],"from":[59],"the":[60,77,81,105,108,114,118,133,167,201],"model":[62],"as":[63],"prompts":[64],"for":[65],"SELD":[66,82,119,170],"specific":[69],"class.":[71],"The":[72],"proposed":[73,109,190],"SS-SELD":[74],"method":[75],"enhances":[76,113],"overall":[78,115],"performance":[79,116,168],"system,":[83,120],"resulting":[84,121],"improved":[86,123],"accuracy":[87],"robustness":[89,126],"contrast":[94],"many":[96],"other":[97],"classification":[98],"methods":[99],"that":[100,158],"can":[101],"be":[102],"affected":[103],"interference":[106],"events,":[107],"framework":[112,191],"accuracies":[124],"When":[130],"evaluated":[131],"on":[132],"Sony-TAu":[134],"Realistic":[135],"Spatial":[136],"Soundscapes":[137],"2023":[138,205],"(STARSS23)":[139],"dataset,":[140],"demonstrate":[142],"significant":[143],"improvements":[144],"both":[146],"(SED)":[150],"direction-of-arrival":[152],"(DOA)":[153],"estimation.":[154],"Our":[155],"findings":[156],"suggest":[157],"is":[161],"promising":[163],"strategy":[164],"enhance":[166],"systems,":[171],"particularly":[172],"scenarios":[174],"overlaps":[177],"classes.":[186],"addition,":[188],"our":[189,196],"had":[192],"contributed":[193],"building":[194],"champion":[197],"systems":[198],"submitted":[199],"Challenge":[202],"DCASE":[204],"Task":[206],"3.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
