{"id":"https://openalex.org/W4372263497","doi":"https://doi.org/10.1109/icassp49357.2023.10094681","title":"An Experimental Study on Sound Event Localization and Detection Under Realistic Testing Conditions","display_name":"An Experimental Study on Sound Event Localization and Detection Under Realistic Testing Conditions","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372263497","doi":"https://doi.org/10.1109/icassp49357.2023.10094681"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/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":true,"raw_author_name":"Shutong Niu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, 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,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, 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,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704805","display_name":"Li Chai","orcid":"https://orcid.org/0000-0001-7906-9913"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Chai","raw_affiliation_strings":["iFLYTEK,Hefei,China","iFLYTEK, Hefei, China"],"affiliations":[{"raw_affiliation_string":"iFLYTEK,Hefei,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060569334","display_name":"Huaxin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaxin Wu","raw_affiliation_strings":["iFLYTEK,Hefei,China","iFLYTEK, Hefei, China"],"affiliations":[{"raw_affiliation_string":"iFLYTEK,Hefei,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK, Hefei, China","institution_ids":[]}]},{"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,China","University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699930","display_name":"Lei Sun","orcid":"https://orcid.org/0000-0001-9960-205X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Sun","raw_affiliation_strings":["iFLYTEK,Hefei,China","iFLYTEK, Hefei, China"],"affiliations":[{"raw_affiliation_string":"iFLYTEK,Hefei,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105518877","display_name":"Yi Fang","orcid":"https://orcid.org/0009-0000-6102-2201"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Fang","raw_affiliation_strings":["iFLYTEK,Hefei,China","iFLYTEK, Hefei, China"],"affiliations":[{"raw_affiliation_string":"iFLYTEK,Hefei,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076812698","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0001-9003-2054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFLYTEK,Hefei,China","iFLYTEK, Hefei, China"],"affiliations":[{"raw_affiliation_string":"iFLYTEK,Hefei,China","institution_ids":[]},{"raw_affiliation_string":"iFLYTEK, Hefei, China","institution_ids":[]}]},{"author_position":"last","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,USA","Georgia Institute of Technology, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5064699619"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":4.2697,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95412155,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7147637605667114},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6579656600952148},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4955388307571411},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47659701108932495},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.47477981448173523},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4426000416278839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3867797553539276},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.353115975856781},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09068465232849121},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08020851016044617},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07223853468894958},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07116076350212097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147637605667114},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6579656600952148},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4955388307571411},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47659701108932495},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.47477981448173523},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4426000416278839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3867797553539276},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.353115975856781},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09068465232849121},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08020851016044617},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07223853468894958},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07116076350212097},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2046317813","https://openalex.org/W2077159900","https://openalex.org/W2135131618","https://openalex.org/W2165320399","https://openalex.org/W2261950180","https://openalex.org/W2342547278","https://openalex.org/W2765407302","https://openalex.org/W2810934215","https://openalex.org/W2936774411","https://openalex.org/W2942551338","https://openalex.org/W2982680886","https://openalex.org/W2998139081","https://openalex.org/W2998508940","https://openalex.org/W3005741390","https://openalex.org/W3083274258","https://openalex.org/W3097777922","https://openalex.org/W3098454764","https://openalex.org/W3117314925","https://openalex.org/W3120252178","https://openalex.org/W3163193264","https://openalex.org/W3163881933","https://openalex.org/W3176079376","https://openalex.org/W3206329344","https://openalex.org/W4282031641","https://openalex.org/W6631190155","https://openalex.org/W6684354967","https://openalex.org/W6704490260","https://openalex.org/W6745136726","https://openalex.org/W6788349323","https://openalex.org/W6797253786","https://openalex.org/W6838853441"],"related_works":["https://openalex.org/W1976985527","https://openalex.org/W2548721895","https://openalex.org/W2373456246","https://openalex.org/W1963716487","https://openalex.org/W2354034738","https://openalex.org/W4386392971","https://openalex.org/W2252747487","https://openalex.org/W4307413935","https://openalex.org/W3158697290","https://openalex.org/W4318718858"],"abstract_inverted_index":{"We":[0],"study":[1],"four":[2,29],"data":[3,13,70,80],"augmentation":[4,71],"(DA)":[5],"techniques":[6],"and":[7,18,51,91],"two":[8,99,113],"model":[9],"architectures":[10],"on":[11,23,32,76],"realistic":[12,34,92,108],"for":[14,62],"sound":[15],"event":[16],"localization":[17],"detection":[19],"(SELD).":[20],"First,":[21],"based":[22],"ResNet-Conformer":[24,101],"(RC),":[25],"we":[26],"compare":[27],"the":[28,33,67,77,98,121,128],"DA":[30],"approaches":[31],"DCASE":[35,129],"2022":[36,130],"SELD":[37,79,105,125],"test":[38],"set":[39,81],"which":[40],"is":[41],"often":[42],"not":[43],"easy":[44],"to":[45,48,87],"handle":[46],"due":[47,86],"room":[49],"reverberations":[50],"audio":[52,63],"overlaps":[53],"in":[54,107,124],"spontaneous":[55],"recordings.":[56],"Experimental":[57],"results":[58],"show":[59],"that,":[60],"except":[61],"channel":[64],"swapping":[65],"(ACS),":[66],"other":[68],"three":[69],"methods":[72],"that":[73],"work":[74],"well":[75],"simulated":[78,90],"are":[82],"no":[83],"longer":[84],"effective":[85],"mismatches":[88],"between":[89],"conditions.":[93,109],"Next,":[94],"using":[95],"ACS-based":[96],"augmentation,":[97],"improved":[100],"networks":[102],"further":[103],"enhance":[104],"performances":[106],"By":[110],"incorporating":[111],"these":[112],"sets":[114],"of":[115,127],"techniques,":[116],"our":[117],"overall":[118],"system":[119],"ranked":[120],"first":[122],"place":[123],"task":[126],"Challenge.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
