{"id":"https://openalex.org/W3030949748","doi":"https://doi.org/10.1109/taslp.2020.2998298","title":"Sound Event Detection Using Multiple Optimized Kernels","display_name":"Sound Event Detection Using Multiple Optimized Kernels","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3030949748","doi":"https://doi.org/10.1109/taslp.2020.2998298","mag":"3030949748"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.2998298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2998298","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5091584895","display_name":"Xianjun Xia","orcid":"https://orcid.org/0000-0001-5277-6634"},"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"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Xianjun Xia","raw_affiliation_strings":["Department of Electrical, Electronic and Computer Engineering of the University of Western Australia, Perth, Australia","MediaLab, Tencent, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-5277-6634","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronic and Computer Engineering of the University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"MediaLab, Tencent, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"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":["Department of Electrical, Electronic and Computer Engineering, The University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3778-4633","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronic and Computer Engineering, The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002219416","display_name":"Ferdous Sohel","orcid":"https://orcid.org/0000-0003-1557-4907"},"institutions":[{"id":"https://openalex.org/I176790772","display_name":"Murdoch University","ror":"https://ror.org/00r4sry34","country_code":"AU","type":"education","lineage":["https://openalex.org/I176790772"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ferdous Sohel","raw_affiliation_strings":["College of Science, Health, Engineering and Education, Murdoch University, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1557-4907","affiliations":[{"raw_affiliation_string":"College of Science, Health, Engineering and Education, Murdoch University, Perth, Australia","institution_ids":["https://openalex.org/I176790772"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727776","display_name":"Yuanjun Zhao","orcid":"https://orcid.org/0000-0002-6153-3543"},"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":"Yuanjun Zhao","raw_affiliation_strings":["Department of Electrical, Electronic and Computer Engineering, The University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6153-3543","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronic and Computer Engineering, The University of Western Australia, Perth, 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":"Defeng Huang","raw_affiliation_strings":["Department of Electrical, Electronic and Computer Engineering, The University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1431-8859","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronic and Computer Engineering, The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2166,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79069919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"28","issue":null,"first_page":"1745","last_page":"1754"},"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":0.9984999895095825,"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":0.9908999800682068,"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/kernel","display_name":"Kernel (algebra)","score":0.7795056104660034},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7730008959770203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7121541500091553},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6685523986816406},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6191454529762268},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6114515066146851},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.586511492729187},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5538589954376221},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49410536885261536},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4861109256744385},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2743624150753021},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12534162402153015},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08116912841796875}],"concepts":[{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7795056104660034},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7730008959770203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7121541500091553},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6685523986816406},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6191454529762268},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6114515066146851},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.586511492729187},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5538589954376221},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49410536885261536},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4861109256744385},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2743624150753021},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12534162402153015},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08116912841796875},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2020.2998298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.2998298","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:researchrepository.murdoch.edu.au:56781","is_oa":false,"landing_page_url":"https://researchrepository.murdoch.edu.au/id/eprint/56781/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400274","display_name":"Murdoch Research Repository (Murdoch University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I176790772","host_organization_name":"Murdoch University","host_organization_lineage":["https://openalex.org/I176790772"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"  Xia, X., Togneri, R., Sohel, F. <https://researchrepository.murdoch.edu.au/view/author/Sohel, Ferdous.html>, Zhao, Y. and Huang, D.   (2020)  Sound event detection using multiple optimized kernels.     IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28 .   pp. 1745-1754.  ","raw_type":"Journal Article"},{"id":"pmh:oai:pure.atira.dk:publications/a52165bb-36e3-4d9d-81be-8195d6c8a554","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85088013982&partnerID=8YFLogxK","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":"Xia , X , Togneri , R , Sohel , F , Zhao , Y & Huang , D 2020 , ' Sound Event Detection Using Multiple Optimized Kernels ' , IEEE/ACM Transactions on Audio Speech and Language Processing , vol. 28 , 9103031 , pp. 1745-1754 . https://doi.org/10.1109/TASLP.2020.2998298","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320991","display_name":"University of Western Australia","ror":"https://ror.org/047272k79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1847088711","https://openalex.org/W1963947681","https://openalex.org/W2086384421","https://openalex.org/W2093328288","https://openalex.org/W2097117768","https://openalex.org/W2119110418","https://openalex.org/W2134426937","https://openalex.org/W2341412280","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2622742434","https://openalex.org/W2752592287","https://openalex.org/W2752693731","https://openalex.org/W2763761345","https://openalex.org/W2763971240","https://openalex.org/W2791367865","https://openalex.org/W2794821752","https://openalex.org/W2810934215","https://openalex.org/W2884011836","https://openalex.org/W2900266038","https://openalex.org/W2950781212","https://openalex.org/W2963723765","https://openalex.org/W2964121744","https://openalex.org/W2964350391","https://openalex.org/W2964355201","https://openalex.org/W2964947054","https://openalex.org/W2995135322","https://openalex.org/W3009927332","https://openalex.org/W3102534672","https://openalex.org/W4288325748","https://openalex.org/W4289329167","https://openalex.org/W6631190155","https://openalex.org/W6638824847","https://openalex.org/W6694260854","https://openalex.org/W6739564277","https://openalex.org/W6744964450","https://openalex.org/W6745117180","https://openalex.org/W6753516609","https://openalex.org/W6763582813","https://openalex.org/W6771478287"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2964954556","https://openalex.org/W3019910406","https://openalex.org/W4386858688","https://openalex.org/W3034421924","https://openalex.org/W2982536526","https://openalex.org/W4380302312","https://openalex.org/W4385338604","https://openalex.org/W2949189996","https://openalex.org/W3081626085"],"abstract_inverted_index":{"Sound":[0],"event":[1,49,65],"detection":[2,40,66],"(SED)":[3],"has":[4],"been":[5],"widely":[6],"applied":[7],"in":[8],"real":[9],"world":[10],"applications.":[11],"Convolutional":[12],"recurrent":[13,71],"neural":[14,72],"network":[15,73],"based":[16,92],"SED":[17],"approaches":[18],"have":[19],"achieved":[20],"state-of-the-art":[21,152],"performance.":[22],"However,":[23],"the":[24,39,44,94,99,102,107,119,131,144,147],"convolution":[25,114],"process":[26],"is":[27],"typically":[28],"performed":[29],"by":[30,53],"using":[31,68],"a":[32,63,69,89],"fixed":[33],"sized":[34],"kernel,":[35],"which":[36],"adversely":[37],"affects":[38],"accuracy":[41],"especially":[42],"when":[43],"acoustic":[45,120],"features":[46],"of":[47,79,101,128,146],"different":[48,80,126],"classes":[50],"are":[51,86,110],"characterized":[52],"high":[54],"variations.":[55,122],"To":[56],"deal":[57,117],"with":[58,75,118],"this,":[59],"this":[60],"article":[61],"proposes":[62],"sound":[64],"technique":[67],"convolutional":[70,77],"framework":[74],"multiple":[76,113],"kernels":[78,85,109],"sizes.":[81],"The":[82],"top":[83],"performing":[84],"selected":[87,108],"from":[88],"kernel":[90],"pool":[91],"on":[93,125],"unsupervised":[95],"clustering":[96],"errors":[97],"and":[98,137],"accuracies":[100],"temporarily":[103],"trained":[104],"models.":[105],"Afterwards,":[106],"fed":[111],"to":[112,116,151],"layers":[115],"feature":[121],"Experimental":[123],"results":[124],"subsets":[127],"AudioSet,":[129],"namely":[130],"DCASE":[132,138],"Challenge":[133,139],"2017":[134],"Task":[135,141],"4":[136],"2018":[140],"4,":[142],"demonstrate":[143],"performance":[145],"proposed":[148],"approach":[149],"compared":[150],"systems.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}