{"id":"https://openalex.org/W4372267873","doi":"https://doi.org/10.1109/icassp49357.2023.10095144","title":"Loss Function Design for DNN-Based Sound Event Localization and Detection on Low-Resource Realistic Data","display_name":"Loss Function Design for DNN-Based Sound Event Localization and Detection on Low-Resource Realistic Data","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372267873","doi":"https://doi.org/10.1109/icassp49357.2023.10095144"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095144","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/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/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":"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"],"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/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,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/A5100704805","display_name":"Li Chai","orcid":"https://orcid.org/0000-0001-7906-9913"},"institutions":[{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Chai","raw_affiliation_strings":["iFlytek,Hefei,China","iFlytek, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek,Hefei,China","institution_ids":["https://openalex.org/I39774598"]},{"raw_affiliation_string":"iFlytek, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060569334","display_name":"Huaxin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"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":["https://openalex.org/I39774598"]},{"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":[{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"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":["https://openalex.org/I39774598"]},{"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,GA,USA","Georgia Institute of Technology, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1086,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77126408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9868999719619751,"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/overfitting","display_name":"Overfitting","score":0.8848767280578613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7426337599754333},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5330832004547119},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5160841345787048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5048421025276184},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48950445652008057},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.44740936160087585},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4457401633262634},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4263896942138672},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41667890548706055}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8848767280578613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7426337599754333},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5330832004547119},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5160841345787048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5048421025276184},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48950445652008057},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.44740936160087585},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4457401633262634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4263896942138672},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41667890548706055},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095144","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":[{"id":"https://metadata.un.org/sdg/8","score":0.4399999976158142,"display_name":"Decent work and economic growth"}],"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":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533561824","https://openalex.org/W1821462560","https://openalex.org/W2046317813","https://openalex.org/W2077159900","https://openalex.org/W2103235956","https://openalex.org/W2113638573","https://openalex.org/W2123843894","https://openalex.org/W2130357996","https://openalex.org/W2165320399","https://openalex.org/W2261950180","https://openalex.org/W2292996718","https://openalex.org/W2466975593","https://openalex.org/W2561817999","https://openalex.org/W2810934215","https://openalex.org/W2936774411","https://openalex.org/W2982680886","https://openalex.org/W2998139081","https://openalex.org/W3035524453","https://openalex.org/W3083274258","https://openalex.org/W3091667472","https://openalex.org/W3117314925","https://openalex.org/W3120252178","https://openalex.org/W3163193264","https://openalex.org/W3186351311","https://openalex.org/W3206329344","https://openalex.org/W3206619923","https://openalex.org/W4221141618","https://openalex.org/W4282031641","https://openalex.org/W4297794384","https://openalex.org/W4312097070","https://openalex.org/W6631190155","https://openalex.org/W6632323398","https://openalex.org/W6638523607","https://openalex.org/W6676344012","https://openalex.org/W6684354967","https://openalex.org/W6784117923","https://openalex.org/W6788349323","https://openalex.org/W6838853441","https://openalex.org/W6842908365"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W4376166922","https://openalex.org/W2490526372","https://openalex.org/W4221142204"],"abstract_inverted_index":{"This":[0],"study":[1],"focuses":[2],"on":[3,31,103,112,156],"the":[4,52,76,95,100,104,113,128,139,142,160,176],"design":[5],"of":[6,75,80,117],"a":[7,11,40,66,91],"loss":[8,96,144,162],"function":[9,97,145,163],"for":[10,43,69,150],"deep":[12],"neural":[13],"network":[14,42,171],"(DNN)-based":[15],"model":[16],"with":[17],"two":[18],"branches,":[19],"which":[20,46],"is":[21],"used":[22],"to":[23,51,57,98,138,167],"solve":[24],"sound":[25,81],"event":[26,49],"localization":[27,86,152],"and":[28,115,120,127,153],"detection":[29,154],"(SELD)":[30],"low-resource":[32],"realistic":[33,157],"data.":[34,158],"To":[35],"this":[36],"end,":[37],"we":[38,63,89],"employ":[39],"secondary":[41],"audio":[44],"classification,":[45],"provides":[47],"global":[48],"information":[50],"main":[53],"network,":[54],"enabling":[55],"it":[56],"make":[58],"robust":[59],"SELD":[60,134],"predictions.":[61],"Furthermore,":[62],"suggest":[64],"utilizing":[65],"momentum":[67],"strategy":[68],"direction-of-arrival":[70],"(DOA)":[71],"estimation,":[72],"taking":[73],"advantage":[74],"strong":[77],"temporal":[78],"consistency":[79],"events,":[82],"thereby":[83],"effectively":[84],"reducing":[85],"error.":[87],"Lastly,":[88],"incorporate":[90],"regularization":[92],"term":[93],"into":[94],"alleviate":[99],"overfitting":[101],"problem":[102],"small":[105],"dataset.":[106],"We":[107],"evaluate":[108],"our":[109],"proposed":[110,143,161],"methods":[111],"Detection":[114],"Classification":[116],"Acoustic":[118],"Scenes":[119],"Events":[121],"(DCASE)":[122],"2022":[123],"Task":[124],"3":[125],"dataset,":[126],"results":[129,149],"demonstrate":[130],"consistent":[131,177],"improvements":[132,178],"in":[133],"performance.":[135],"In":[136],"comparison":[137],"baseline":[140],"system,":[141],"yields":[146],"significantly":[147],"improved":[148],"both":[151],"metrics":[155],"Moreover,":[159],"demonstrates":[164],"its":[165],"ability":[166],"generalize":[168],"across":[169],"different":[170],"architectures,":[172],"as":[173],"evidenced":[174],"by":[175],"achieved.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}