{"id":"https://openalex.org/W3163206520","doi":"https://doi.org/10.1109/icassp39728.2021.9414602","title":"A General Network Architecture for Sound Event Localization and Detection Using Transfer Learning and Recurrent Neural Network","display_name":"A General Network Architecture for Sound Event Localization and Detection Using Transfer Learning and Recurrent Neural Network","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163206520","doi":"https://doi.org/10.1109/icassp39728.2021.9414602","mag":"3163206520"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5039913415","display_name":"Thi Ngoc Tho Nguyen","orcid":"https://orcid.org/0000-0002-0210-6373"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Thi Ngoc Tho Nguyen","raw_affiliation_strings":["School of EEE, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EEE, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065667852","display_name":"Ngoc Khanh Nguyen","orcid":"https://orcid.org/0000-0001-8240-6167"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ngoc Khanh Nguyen","raw_affiliation_strings":["School of EEE, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EEE, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["School of EECS, Queen Mary University of London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EECS, Queen Mary University of London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075250567","display_name":"Lam Pham","orcid":"https://orcid.org/0000-0001-8155-7553"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Lam Pham","raw_affiliation_strings":["Center for Digital Safety and Security, Austrian Institute of Technology, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Digital Safety and Security, Austrian Institute of Technology, Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086986606","display_name":"Kenneth Ooi","orcid":"https://orcid.org/0000-0001-5629-6275"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kenneth Ooi","raw_affiliation_strings":["School of EEE, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EEE, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105462806","display_name":"Douglas L. Jones","orcid":"https://orcid.org/0000-0002-7817-7629"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas L. Jones","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072584895","display_name":"Woon\u2010Seng Gan","orcid":"https://orcid.org/0000-0002-7143-1823"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Woon-Seng Gan","raw_affiliation_strings":["School of EEE, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of EEE, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"935","last_page":"939"},"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":0.9990000128746033,"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":0.9918000102043152,"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":0.7109586000442505},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5766825675964355},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.566325843334198},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5424791574478149},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5324958562850952},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5142428278923035},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5113243460655212},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45077231526374817},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.4500102698802948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42706137895584106},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3860059976577759},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10684940218925476},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06898492574691772}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7109586000442505},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5766825675964355},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.566325843334198},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5424791574478149},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5324958562850952},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5142428278923035},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5113243460655212},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45077231526374817},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.4500102698802948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42706137895584106},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3860059976577759},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10684940218925476},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06898492574691772},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414602","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/74441","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/74441","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1422086691","https://openalex.org/W1964998538","https://openalex.org/W2139129402","https://openalex.org/W2292996718","https://openalex.org/W2509065397","https://openalex.org/W2511089602","https://openalex.org/W2518102674","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2810934215","https://openalex.org/W2942551338","https://openalex.org/W2998139081","https://openalex.org/W3005741390","https://openalex.org/W3033731578","https://openalex.org/W3035333188","https://openalex.org/W3081461453","https://openalex.org/W3085832277","https://openalex.org/W3091667472","https://openalex.org/W3094550259","https://openalex.org/W3098357269","https://openalex.org/W3098454764","https://openalex.org/W4287766186","https://openalex.org/W6628353819","https://openalex.org/W6771438384","https://openalex.org/W6779923105","https://openalex.org/W6782995065","https://openalex.org/W6784117923"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W1889624880","https://openalex.org/W2229372569"],"abstract_inverted_index":{"Polyphonic":[0],"sound":[1,17,77,82],"event":[2,18],"detection":[3,19],"and":[4,21,50,54,62,79,97,111,147,151],"localization":[5],"(SELD)":[6],"task":[7],"is":[8,12,105,116,171],"challenging":[9],"because":[10],"it":[11],"difficult":[13],"to":[14,47],"jointly":[15],"optimize":[16],"(SED)":[20],"direction-of-arrival":[22],"(DOA)":[23],"estimation":[24,52,64,99,113,149],"in":[25,37],"the":[26,39,60,73,76,94,120,130,137,166],"same":[27],"network.":[28],"We":[29],"propose":[30],"a":[31,55],"general":[32],"network":[33,41,103,142,169],"architecture":[34,104,143,170],"for":[35,165],"SELD":[36,40,67,133,160,168],"which":[38],"comprises":[42],"sub-networks":[43,121],"that":[44,58,136],"are":[45,91,155],"pre-trained":[46],"solve":[48],"SED":[49,61,96,110,146],"DOA":[51,63,98,112,148],"independently,":[53],"recurrent":[56,70],"layer":[57,71],"combines":[59],"outputs":[65,90],"into":[66],"outputs.":[68],"The":[69,126,162],"does":[72],"alignment":[74],"between":[75],"classes":[78],"DOAs":[80],"of":[81,87,139],"events":[83],"while":[84],"being":[85],"unaware":[86],"how":[88],"these":[89],"produced":[92],"by":[93],"upstream":[95],"algorithms.":[100,114,161],"This":[101],"simple":[102],"compatible":[106],"with":[107,157],"different":[108,145,152],"existing":[109],"It":[115],"highly":[117],"practical":[118],"since":[119],"can":[122],"be":[123],"improved":[124],"independently.":[125],"experimental":[127],"results":[128],"using":[129,144],"DCASE":[131],"2020":[132],"dataset":[134],"show":[135],"performances":[138],"our":[140],"proposed":[141,167],"algorithms":[150],"audio":[153],"formats":[154],"competitive":[156],"other":[158],"state-of-the-art":[159],"source":[163],"code":[164],"available":[172],"at":[173],"Github":[174],"<sup":[175],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[176],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[177],".":[178]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
