{"id":"https://openalex.org/W3135042544","doi":"https://doi.org/10.1109/iscslp49672.2021.9362116","title":"A Model Ensemble Approach for Sound Event Localization and Detection","display_name":"A Model Ensemble Approach for Sound Event Localization and Detection","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3135042544","doi":"https://doi.org/10.1109/iscslp49672.2021.9362116","mag":"3135042544"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"conference-paper","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/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"],"raw_orcid":null,"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/A5035180322","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"],"raw_orcid":null,"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/A5104307432","display_name":"Zijun Jing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijun Jing","raw_affiliation_strings":["iFLYTEK,Hefei,China","iFLYTEK, Hefei, China"],"raw_orcid":null,"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/A5079840202","display_name":"Feng Ma","orcid":"https://orcid.org/0009-0004-5289-8075"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Ma","raw_affiliation_strings":["iFLYTEK,Hefei,China","iFLYTEK, Hefei, China"],"raw_orcid":null,"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/A5067418255","display_name":"Yi Fang","orcid":"https://orcid.org/0000-0002-1538-249X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Fang","raw_affiliation_strings":["iFLYTEK,Hefei,China","iFLYTEK, Hefei, China"],"raw_orcid":null,"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/A5101664515","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0009-0005-3508-3736"},"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":"Yuxuan Wang","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"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/A5036705655","display_name":"Tairan Chen","orcid":"https://orcid.org/0000-0003-0241-4314"},"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":"Tairan Chen","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China","University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"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/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"],"raw_orcid":null,"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/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"],"raw_orcid":null,"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":"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"],"raw_orcid":null,"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9872999787330627,"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/computer-science","display_name":"Computer science","score":0.7629663944244385},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6885334253311157},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6684800982475281},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6421789526939392},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.635163426399231},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6310739517211914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5779746174812317},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5235133767127991},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5107204914093018},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4880572557449341},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.41048163175582886},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3294876217842102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7629663944244385},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6885334253311157},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6684800982475281},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6421789526939392},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.635163426399231},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6310739517211914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5779746174812317},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5235133767127991},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5107204914093018},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4880572557449341},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41048163175582886},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3294876217842102},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"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":36,"referenced_works":["https://openalex.org/W1422086691","https://openalex.org/W1501987291","https://openalex.org/W1533561824","https://openalex.org/W1970578576","https://openalex.org/W1972567154","https://openalex.org/W2090200552","https://openalex.org/W2103088716","https://openalex.org/W2110412069","https://openalex.org/W2113638573","https://openalex.org/W2128131274","https://openalex.org/W2130357996","https://openalex.org/W2168441989","https://openalex.org/W2194775991","https://openalex.org/W2292996718","https://openalex.org/W2341412280","https://openalex.org/W2407005679","https://openalex.org/W2531409750","https://openalex.org/W2591013610","https://openalex.org/W2810934215","https://openalex.org/W2883135409","https://openalex.org/W2888867175","https://openalex.org/W2897282582","https://openalex.org/W2897361856","https://openalex.org/W2942551338","https://openalex.org/W2962708126","https://openalex.org/W2963099423","https://openalex.org/W2964342924","https://openalex.org/W2982429715","https://openalex.org/W2998139081","https://openalex.org/W3016037102","https://openalex.org/W3033731578","https://openalex.org/W3098454764","https://openalex.org/W4287766186","https://openalex.org/W6628353819","https://openalex.org/W6632323398","https://openalex.org/W6779923105"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4313906399","https://openalex.org/W4321487865","https://openalex.org/W2811106690","https://openalex.org/W4239306820","https://openalex.org/W2947043951","https://openalex.org/W2318112981","https://openalex.org/W4312417841","https://openalex.org/W4225147082","https://openalex.org/W2969228573"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,46,51,57,70,146],"model":[6,90,157,194],"ensemble":[7,158,195],"approach":[8,170],"for":[9,110,116,140],"sound":[10,26,186],"event":[11,27,187],"localization":[12,188],"and":[13,30,56,113,130,152,159,165,174,189],"detection":[14,28],"(SELD).":[15],"We":[16],"adopt":[17],"several":[18,135],"deep":[19,191],"neural":[20,74,192],"network":[21,75,136],"(DNN)":[22],"architectures":[23,137],"to":[24,78,89],"perform":[25],"(SED)":[29],"direction-of-arrival":[31],"(DOA)":[32],"estimation":[33,112],"simultaneously.":[34],"Generally,":[35],"the":[36,61,96,105,114,125,141,163,168,176],"DNN":[37],"architecture":[38],"consists":[39],"of":[40,72,122,150],"three":[41],"modules":[42],"stacked":[43],"together,":[44],"i.e,":[45],"High-level":[47,64,126],"Feature":[48,65,127],"Representation":[49,54,66,86,128,133],"module,":[50,55,134],"Temporal":[52,84,131],"Context":[53,85,132],"Fully-connected":[58,106],"module":[59,67,87,107,129],"in":[60,95,104,124,179],"end.":[62],"The":[63,83],"usually":[68],"contains":[69],"series":[71],"convolutional":[73],"(CNN)":[76],"layers":[77],"extract":[79],"useful":[80],"local":[81],"features.":[82,98],"aims":[88],"longer":[91],"temporal":[92],"context":[93],"dependency":[94],"extracted":[97],"There":[99],"are":[100,138],"two":[101],"parallel":[102],"branches":[103],"with":[108],"one":[109],"SED":[111,151],"other":[115],"DOA":[117,153],"estimation.":[118],"With":[119],"different":[120],"combinations":[121],"implementation":[123],"used":[139],"SELD":[142],"task.":[143],"At":[144],"last,":[145],"more":[147],"robust":[148],"prediction":[149],"is":[154],"obtained":[155],"by":[156],"post-processing.":[160],"Tested":[161],"on":[162],"development":[164],"evaluation":[166],"datasets,":[167],"proposed":[169],"achieves":[171],"promising":[172],"results":[173],"ranks":[175],"first":[177],"place":[178],"DCASE":[180],"2020":[181],"task3":[182],"challenge.":[183],"Index":[184],"Terms:":[185],"detection,":[190],"network,":[193]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}