{"id":"https://openalex.org/W3083274258","doi":"https://doi.org/10.1109/taslp.2020.3047233","title":"Overview and Evaluation of Sound Event Localization and Detection in DCASE 2019","display_name":"Overview and Evaluation of Sound Event Localization and Detection in DCASE 2019","publication_year":2020,"publication_date":"2020-12-24","ids":{"openalex":"https://openalex.org/W3083274258","doi":"https://doi.org/10.1109/taslp.2020.3047233","mag":"3083274258"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3047233","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3047233","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09306885.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09306885.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010846139","display_name":"Archontis Politis","orcid":"https://orcid.org/0000-0002-0595-2356"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Archontis Politis","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0002-0595-2356","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0002-6640-9752","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054490307","display_name":"Sharath Adavanne","orcid":"https://orcid.org/0000-0002-5001-6911"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sharath Adavanne","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0002-5001-6911","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059929826","display_name":"Toni Heittola","orcid":"https://orcid.org/0000-0002-8855-0415"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Toni Heittola","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0002-8855-0415","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"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/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0002-4604-9729","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010846139"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":10.7871,"has_fulltext":true,"cited_by_count":132,"citation_normalized_percentile":{"value":0.99033375,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"29","issue":null,"first_page":"684","last_page":"698"},"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":0.9987999796867371,"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":0.9897000193595886,"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/event","display_name":"Event (particle physics)","score":0.7894902229309082},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7723037004470825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7525002956390381},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6948824524879456},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.53741455078125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.521524965763092},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.46679219603538513},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4516425132751465},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43453487753868103},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40564417839050293},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34776878356933594},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11931899189949036},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.10643196105957031},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07822877168655396}],"concepts":[{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7894902229309082},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7723037004470825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7525002956390381},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6948824524879456},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.53741455078125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.521524965763092},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.46679219603538513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4516425132751465},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43453487753868103},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40564417839050293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34776878356933594},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11931899189949036},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.10643196105957031},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07822877168655396},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2020.3047233","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3047233","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09306885.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:arXiv.org:2009.02792","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.02792","pdf_url":"https://arxiv.org/pdf/2009.02792","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:trepo.tuni.fi:10024/215589","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/215589","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2020.3047233","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3047233","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9289074/09306885.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3226960623","display_name":null,"funder_award_id":"637422 EVERYSOUND","funder_id":"https://openalex.org/F4320334678","funder_display_name":"European Research Council"}],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3083274258.pdf","grobid_xml":"https://content.openalex.org/works/W3083274258.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1422086691","https://openalex.org/W1557595030","https://openalex.org/W2044063703","https://openalex.org/W2078483536","https://openalex.org/W2103235956","https://openalex.org/W2124781496","https://openalex.org/W2126885789","https://openalex.org/W2135131618","https://openalex.org/W2165320399","https://openalex.org/W2167994833","https://openalex.org/W2222512263","https://openalex.org/W2261950180","https://openalex.org/W2408239454","https://openalex.org/W2592401976","https://openalex.org/W2765407302","https://openalex.org/W2772956764","https://openalex.org/W2775794021","https://openalex.org/W2807015669","https://openalex.org/W2810934215","https://openalex.org/W2885219692","https://openalex.org/W2913340405","https://openalex.org/W2917254586","https://openalex.org/W2929983093","https://openalex.org/W2931658998","https://openalex.org/W2936774411","https://openalex.org/W2938440247","https://openalex.org/W2942551338","https://openalex.org/W2963399829","https://openalex.org/W2964342924","https://openalex.org/W2982070294","https://openalex.org/W2982341288","https://openalex.org/W2982382207","https://openalex.org/W2982429715","https://openalex.org/W2982440118","https://openalex.org/W2982440425","https://openalex.org/W2982477635","https://openalex.org/W2982537717","https://openalex.org/W2982549770","https://openalex.org/W2982574022","https://openalex.org/W2982680886","https://openalex.org/W2982681313","https://openalex.org/W2998139081","https://openalex.org/W3005353199","https://openalex.org/W3005741390","https://openalex.org/W3016252974","https://openalex.org/W3033731578","https://openalex.org/W3041391240","https://openalex.org/W3098454764","https://openalex.org/W3124180505","https://openalex.org/W4287766186","https://openalex.org/W4288375019","https://openalex.org/W6628353819","https://openalex.org/W6633511732","https://openalex.org/W6684354967","https://openalex.org/W6745136726","https://openalex.org/W6761152316","https://openalex.org/W6773738941","https://openalex.org/W6775239391","https://openalex.org/W6779923105","https://openalex.org/W6983550193"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2915512527","https://openalex.org/W51364034","https://openalex.org/W2793336762","https://openalex.org/W2091548507","https://openalex.org/W4385572368"],"abstract_inverted_index":{"Sound":[0],"event":[1,46,141,187],"localization":[2,47,139],"and":[3,27,48,80,100,102,124,140],"detection":[4,216],"is":[5],"a":[6,52,161],"novel":[7],"area":[8],"of":[9,17,24,30,32,39,54,63,77,83,105,113,121,145,156,163,181,186,195,207],"research":[10],"that":[11,174,198],"emerged":[12],"from":[13],"the":[14,19,25,40,55,70,84,96,103,106,132,146,153,157,178,183,196,203],"combined":[15],"interest":[16],"analyzing":[18],"acoustic":[20],"scene":[21],"in":[22,86,93,111,131,202],"terms":[23,112],"spatial":[26],"temporal":[28],"activity":[29],"sounds":[31],"interest.":[33],"This":[34],"paper":[35],"presents":[36,92],"an":[37,87],"overview":[38,91,147],"first":[41],"international":[42],"evaluation":[43,82],"on":[44,136,149,177,215,222],"sound":[45,65],"detection,":[49],"organized":[50],"as":[51],"task":[53,180],"DCASE":[56],"2019":[57],"Challenge.":[58],"A":[59],"large-scale":[60],"realistic":[61],"dataset":[62],"spatialized":[64],"events":[66],"was":[67,134,224],"generated":[68],"for":[69,75,81,152],"challenge,":[71],"to":[72,189],"be":[73],"used":[74],"training":[76,118],"learning-based":[78],"approaches,":[79,119],"submissions":[85,164,173,197,208],"unlabeled":[88],"subset.":[89],"The":[90,169],"detail":[94],"how":[95],"systems":[97],"were":[98,199],"evaluated":[99,213],"ranked":[101,200],"characteristics":[104],"best-performing":[107],"systems.":[108],"Common":[109],"strategies":[110],"input":[114],"features,":[115],"model":[116],"architectures,":[117],"exploitation":[120],"prior":[122],"knowledge,":[123],"data":[125],"augmentation":[126],"are":[127],"discussed.":[128],"Since":[129],"ranking":[130,206],"challenge":[133],"based":[135],"individually":[137],"evaluating":[138],"classification":[142],"performance,":[143],"part":[144],"focuses":[148],"presenting":[150],"metrics":[151],"joint":[154,179],"measurement":[155],"two,":[158],"together":[159],"with":[160],"reevaluation":[162],"using":[165],"these":[166],"new":[167,170],"metrics.":[168],"analysis":[171],"reveals":[172],"performed":[175,210],"better":[176],"detecting":[182],"correct":[184],"type":[185],"close":[188],"its":[190],"original":[191],"location":[192],"than":[193],"some":[194],"higher":[201],"challenge.":[204],"Consequently,":[205],"which":[209],"strongly":[211],"when":[212],"separately":[214],"or":[217],"localization,":[218],"but":[219],"not":[220],"jointly":[221],"both,":[223],"affected":[225],"negatively.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":24},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":2}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2021-01-05T00:00:00"}
