{"id":"https://openalex.org/W2810934215","doi":"https://doi.org/10.1109/jstsp.2018.2885636","title":"Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks","display_name":"Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks","publication_year":2018,"publication_date":"2018-12-07","ids":{"openalex":"https://openalex.org/W2810934215","doi":"https://doi.org/10.1109/jstsp.2018.2885636","mag":"2810934215"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2018.2885636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2018.2885636","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1807.00129","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054490307","display_name":"Sharath Adavanne","orcid":"https://orcid.org/0000-0002-5001-6911"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Sharath Adavanne","raw_affiliation_strings":["Signal Processing Laboratory, Tampere University of Technology, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0002-5001-6911","affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010846139","display_name":"Archontis Politis","orcid":"https://orcid.org/0000-0002-0595-2356"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Archontis Politis","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-0595-2356","affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057962401","display_name":"Joonas Nikunen","orcid":"https://orcid.org/0000-0001-6092-9346"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Joonas Nikunen","raw_affiliation_strings":["Signal Processing Laboratory, Tampere University of Technology, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0001-6092-9346","affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Signal Processing Laboratory, Tampere University of Technology, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0002-4604-9729","affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054490307"],"corresponding_institution_ids":["https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":27.7552,"has_fulltext":false,"cited_by_count":511,"citation_normalized_percentile":{"value":0.99797769,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"13","issue":"1","first_page":"34","last_page":"48"},"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":0.9926999807357788,"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":0.717793345451355},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6273291110992432},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5864384174346924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5094733834266663},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4961851239204407},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4586612582206726},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38171035051345825},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3485219478607178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717793345451355},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6273291110992432},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5864384174346924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5094733834266663},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4961851239204407},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4586612582206726},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38171035051345825},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3485219478607178},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jstsp.2018.2885636","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2018.2885636","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1807.00129","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.00129","pdf_url":"https://arxiv.org/pdf/1807.00129","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/36994","is_oa":true,"landing_page_url":"https://aaltodoc.aalto.fi/handle/123456789/36994","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"A1 Alkuper\u00e4isartikkeli tieteellisess\u00e4 aikakauslehdess\u00e4"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1807.00129","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.00129","pdf_url":"https://arxiv.org/pdf/1807.00129","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2327472798","display_name":"Computational Analysis of Everyday Soundscapes","funder_award_id":"637422","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W126779258","https://openalex.org/W1422086691","https://openalex.org/W1501987291","https://openalex.org/W1522301498","https://openalex.org/W1529830495","https://openalex.org/W1533561824","https://openalex.org/W1536644969","https://openalex.org/W1555217905","https://openalex.org/W1587644769","https://openalex.org/W1589236794","https://openalex.org/W1603075283","https://openalex.org/W1650531274","https://openalex.org/W1836465849","https://openalex.org/W1844944916","https://openalex.org/W1978092817","https://openalex.org/W2038484192","https://openalex.org/W2040910067","https://openalex.org/W2093010905","https://openalex.org/W2103088716","https://openalex.org/W2110412069","https://openalex.org/W2113638573","https://openalex.org/W2113744809","https://openalex.org/W2117678320","https://openalex.org/W2128131274","https://openalex.org/W2130640900","https://openalex.org/W2132920253","https://openalex.org/W2161020307","https://openalex.org/W2165320399","https://openalex.org/W2167994833","https://openalex.org/W2171680721","https://openalex.org/W2261950180","https://openalex.org/W2289394825","https://openalex.org/W2292996718","https://openalex.org/W2341412280","https://openalex.org/W2403149086","https://openalex.org/W2408239454","https://openalex.org/W2541714600","https://openalex.org/W2551990143","https://openalex.org/W2586642235","https://openalex.org/W2591013610","https://openalex.org/W2592109325","https://openalex.org/W2611943505","https://openalex.org/W2622742434","https://openalex.org/W2625023227","https://openalex.org/W2746554716","https://openalex.org/W2748560825","https://openalex.org/W2758358029","https://openalex.org/W2763761345","https://openalex.org/W2771922328","https://openalex.org/W2772736377","https://openalex.org/W2772956764","https://openalex.org/W2775505379","https://openalex.org/W2962708126","https://openalex.org/W2963099423","https://openalex.org/W2963128891","https://openalex.org/W2963158330","https://openalex.org/W2964121744","https://openalex.org/W2964342924","https://openalex.org/W2972079735","https://openalex.org/W3104757150","https://openalex.org/W3105684258","https://openalex.org/W4206633762","https://openalex.org/W6628353819","https://openalex.org/W6631190155","https://openalex.org/W6632323398","https://openalex.org/W6638667902","https://openalex.org/W6684354967","https://openalex.org/W6729017730","https://openalex.org/W6739564277","https://openalex.org/W6744964450","https://openalex.org/W6746576432","https://openalex.org/W6747331233","https://openalex.org/W6767570136"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W2982145560","https://openalex.org/W2969450769"],"abstract_inverted_index":{"In":[0],"this":[1,119,241],"paper,":[2],"we":[3],"propose":[4],"a":[5,31,60,222,255],"convolutional":[6],"recurrent":[7],"neural":[8],"network":[9,29],"for":[10,71,94,254],"joint":[11],"sound":[12,21,53,74,96,113,170,260],"event":[13,54,75,97,114],"localization":[14,81],"and":[15,40,116,132,150,161,175,189,202,214],"detection":[16,55],"(SELD)":[17],"of":[18,33,90,135,226,230,258],"multiple":[19,109],"overlapping":[20,169,259],"events":[22,171],"in":[23,46,172,234],"three-dimensional":[24],"(3-D)":[25],"space.":[26],"The":[27,102,125,154,178,193,218],"proposed":[28,103,126,179,198,219],"takes":[30],"sequence":[32],"consecutive":[34],"spectrogram":[35,137],"time":[36,66],"frames":[37],"as":[38,59,143],"input":[39],"maps":[41],"it":[42],"to":[43,107,123,204,209,236,245],"two":[44,162,184],"outputs":[45],"parallel.":[47],"As":[48,77],"the":[49,52,73,78,86,91,130,136,144,197,227,237,250],"first":[50],"output,":[51,80],"(SED)":[56],"is":[57,82,105,156,181,200],"performed":[58,83],"multi-label":[61],"classification":[62],"task":[63],"on":[64,139,158],"each":[65,95,140],"frame":[67],"producing":[68],"temporal":[69],"activity":[70],"all":[72],"classes.":[76],"second":[79],"by":[84],"estimating":[85],"3-D":[87],"Cartesian":[88],"coordinates":[89],"direction-of-arrival":[92],"(DOA)":[93],"class":[98],"using":[99],"multi-output":[100],"regression.":[101],"method":[104,127,155,180,199,220,253],"able":[106],"associate":[108],"DOAs":[110,231],"with":[111,121,167,183],"respective":[112],"labels":[115],"further":[117],"track":[118],"association":[120],"respect":[122],"time.":[124],"uses":[128],"separately":[129],"phase":[131],"magnitude":[133],"component":[134],"calculated":[138],"audio":[141],"channel":[142],"feature,":[145],"thereby":[146],"avoiding":[147],"any":[148,205],"method-":[149],"array-specific":[151],"feature":[152],"extraction.":[153],"evaluated":[157],"five":[159],"Ambisonic":[160],"circular":[163],"array":[164,206],"format":[165],"datasets":[166,233],"different":[168],"anechoic,":[173],"reverberant,":[174],"real-life":[176],"scenarios.":[177,217],"compared":[182],"SED,":[185],"three":[186],"DOA":[187,211],"estimation,":[188],"one":[190],"SELD":[191],"baselines.":[192],"results":[194],"show":[195],"that":[196],"generic":[201],"applicable":[203],"structures,":[207],"robust":[208],"unseen":[210],"values,":[212],"reverberation,":[213],"low":[215],"SNR":[216],"achieved":[221],"consistently":[223],"higher":[224,256],"recall":[225,242],"estimated":[228],"number":[229,257],"across":[232],"comparison":[235],"best":[238,251],"baseline.":[239],"Additionally,":[240],"was":[243],"observed":[244],"be":[246],"significantly":[247],"better":[248],"than":[249],"baseline":[252],"events.":[261]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":62},{"year":2024,"cited_by_count":91},{"year":2023,"cited_by_count":85},{"year":2022,"cited_by_count":80},{"year":2021,"cited_by_count":72},{"year":2020,"cited_by_count":60},{"year":2019,"cited_by_count":35}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2018-07-10T00:00:00"}