{"id":"https://openalex.org/W4393808447","doi":"https://doi.org/10.5281/zenodo.7880637","title":"STARSS23: Sony-TAu Realistic Spatial Soundscapes 2023","display_name":"STARSS23: Sony-TAu Realistic Spatial Soundscapes 2023","publication_year":2023,"publication_date":"2023-03-08","ids":{"openalex":"https://openalex.org/W4393808447","doi":"https://doi.org/10.5281/zenodo.7880637"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:7880637","is_oa":true,"landing_page_url":"https://zenodo.org/record/7880637","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/other"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/7880637","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":"Politis, Archontis","raw_affiliation_strings":["Tampere University"],"raw_orcid":"https://orcid.org/0000-0002-0595-2356","affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051965288","display_name":"Kazuki Shimada","orcid":"https://orcid.org/0000-0001-5389-2346"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shimada, Kazuki","raw_affiliation_strings":["SONY"],"raw_orcid":"https://orcid.org/0000-0001-5389-2346","affiliations":[{"raw_affiliation_string":"SONY","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022669956","display_name":"Parthasaarathy Sudarsanam","orcid":"https://orcid.org/0009-0009-3751-6469"},"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":"Sudarsanam, Parthasaarathy","raw_affiliation_strings":["Tampere University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065974929","display_name":"Aapo Hakala","orcid":null},"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":"Hakala, Aapo","raw_affiliation_strings":["Tampere University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104117184","display_name":"Shusuke Takahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takahashi, Shusuke","raw_affiliation_strings":["SONY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SONY","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108913642","display_name":"Daniel Alexander Krause","orcid":null},"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":"Krause, Daniel Alexander","raw_affiliation_strings":["Tampere University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101589290","display_name":"Naoya Takahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takahashi, Naoya","raw_affiliation_strings":["SONY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SONY","institution_ids":["https://openalex.org/I2800278093"]}]},{"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":"Adavanne, Sharath","raw_affiliation_strings":["Tampere University"],"raw_orcid":"https://orcid.org/0000-0002-5001-6911","affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017785136","display_name":"Yuichiro Koyama","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koyama, Yuichiro","raw_affiliation_strings":["SONY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SONY","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104321727","display_name":"Kengo Uchida","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Uchida, Kengo","raw_affiliation_strings":["SONY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SONY","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitsufuji, Yuki","raw_affiliation_strings":["SONY"],"raw_orcid":"https://orcid.org/0000-0002-6806-6140","affiliations":[{"raw_affiliation_string":"SONY","institution_ids":["https://openalex.org/I2800278093"]}]},{"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":"Virtanen, Tuomas","raw_affiliation_strings":["Tampere University"],"raw_orcid":"https://orcid.org/0000-0002-4604-9729","affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5010846139"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11692","display_name":"Noise Effects and Management","score":0.4805999994277954,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11692","display_name":"Noise Effects and Management","score":0.4805999994277954,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/soundscape","display_name":"Soundscape","score":0.5383509397506714},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.3740403652191162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3503159284591675},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.33795422315597534},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.19881489872932434},{"id":"https://openalex.org/keywords/geomorphology","display_name":"Geomorphology","score":0.0571824312210083},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.0562901496887207}],"concepts":[{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.5383509397506714},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.3740403652191162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3503159284591675},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.33795422315597534},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.19881489872932434},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0571824312210083},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.0562901496887207}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:7880637","is_oa":true,"landing_page_url":"https://zenodo.org/record/7880637","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.7880637","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.7880637","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:7880637","is_oa":true,"landing_page_url":"https://zenodo.org/record/7880637","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.4300000071525574,"display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W4393414957","https://openalex.org/W4393421431","https://openalex.org/W4393636207","https://openalex.org/W4393719440"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1254698036","https://openalex.org/W2896201871","https://openalex.org/W1988083194","https://openalex.org/W2282503792","https://openalex.org/W2365709658","https://openalex.org/W1562588264","https://openalex.org/W1593731728","https://openalex.org/W2308616044","https://openalex.org/W1482410789"],"abstract_inverted_index":{"<strong>DESCRIPTION:</strong>":[0],"The":[1,36,70,113,326,500,560,968,1015,1128,1206,1218,1230,1241,1252,1268,1284],"<strong>Sony-TAu":[2],"Realistic":[3],"Spatial":[4,216,222,228,429,686],"Soundscapes":[5],"2023":[6,100,110,1071,1113],"(STARSS23)</strong>":[7],"dataset":[8,37,71,96,115,178,242,386,467,502,533,561,950,1056,1098,1135],"contains":[9,243,1244,1287],"multichannel":[10],"recordings":[11,91,137,157,175,244,330,343,470,680,801,835,849,863,877,927,938,1139,1145],"of":[12,26,33,53,107,119,156,163,176,195,209,214,236,245,254,257,260,273,296,306,320,329,342,354,428,431,437,468,471,477,482,487,509,539,564,569,576,588,619,629,657,664,702,711,723,741,761,772,782,793,803,814,1017,1019,1025,1029,1043,1086,1133,1152,1155,1185,1213,1225,1259,1275,1295,1307],"sound":[13,192,212,247,277,309,478,513,518,631,963],"scenes":[14,213,248,473,669],"in":[15,40,44,58,74,138,147,159,322,610,624,652,655,678,746,750,754,775,796,817,844,858,872,886,954,1068,1110],"various":[16],"rooms":[17,744,846,860,874,888],"and":[18,23,57,67,85,104,169,199,226,249,280,304,308,314,318,336,349,372,396,443,485,490,507,527,556,567,578,634,650,681,736,752,906,1052,1075,1094,1117,1140,1142,1160,1166,1309],"environments,":[19],"together":[20],"with":[21,128,233,434,474,521,592,768,789,810,939,1054,1096],"temporal":[22],"spatial":[24,77,211,284,373,469,594,662],"annotations":[25,267,374,476,687],"prominent":[27],"events":[28,307,691,700,716,725,1024],"belonging":[29],"to":[30,172,204,713,727,1023,1158,1178,1210,1222,1256,1272,1304,1315],"a":[31,64,80,117,271,593,620,625,643,769,790,811,1026,1044,1087],"set":[32,162],"target":[34,288,674,704,962],"classes.":[35],"is":[38,72,116,311,503,617,825,1057,1099],"collected":[39,332,345],"two":[41,75,611],"different":[42,370,612],"countries,":[43],"Tampere,":[45],"Finland":[46],"by":[47,61,293,684,694,837,851,865,879,930,1149],"the":[48,94,98,108,120,125,129,139,160,164,173,177,189,196,205,237,240,255,286,294,297,300,323,357,369,483,532,565,570,584,653,665,668,679,703,747,831,840,854,868,882,949,955,972,1036,1065,1069,1079,1107,1111,1121,1134,1143,1150,1171,1183,1197,1214,1226,1234,1245,1260,1265,1276,1281,1288,1296,1300,1305],"Audio":[49],"Researh":[50],"Group":[51],"(ARG)":[52],"<strong>Tampere":[54],"University":[55],"(TAU)</strong>,":[56],"Tokyo,":[59],"Japan":[60],"<strong>SONY</strong>,":[62],"using":[63,830],"similar":[65],"setup":[66],"annotation":[68,397],"procedure.":[69],"delivered":[73],"4-channel":[76,899],"recording":[78,150,615,621,759,780,901,1228,1262,1278],"formats,":[79],"microphone":[81,908],"array":[82,909],"one":[83,88],"(<strong>MIC</strong>),":[84],"first-order":[86,903],"Ambisonics":[87,904],"(<strong>FOA</strong>).":[89],"These":[90],"serve":[92,1063,1105],"as":[93,551,597,708,1064,1106,1200],"development":[95,140,832,1137],"for":[97,188,276,283,505,512,537,573,639,688,827,839,853,867,881,1170,1237,1248,1264,1280,1291],"DCASE":[99,109,238,1070,1112],"Sound":[101,217,223,229,438,699,1072,1114],"Event":[102,1073,1115],"Localization":[103,1074,1116],"Detection":[105,484,1076,1118],"Task":[106,1153],"Challenge.<br>":[111],"<br>":[112,352,440],"STARSS23":[114,585],"continuation":[118],"STARSS22":[121],"dataset.":[122,165,833,1298],"It":[123],"extends":[124],"previous":[126,197,207,234],"version":[127,1130],"following:":[130],"An":[131,152,425,1041],"additional":[132],"<strong>additional":[133,153],"2hrs":[134],"30mins":[135],"</strong>of":[136],"set,":[141],"from":[142,180,356,363,935],"<strong>5":[143],"new":[144,149],"rooms</strong>":[145],"distributed":[146],"47":[148],"clips.":[151],"1hr":[154],"40mins</strong>":[155],"added":[158],"evaluation":[161,508,538,563,587,1144,1173,1198,1266,1282,1297],"<strong>360\u00b0":[166],"videos</strong>":[167],"spatially":[168,190],"temporally":[170],"aligned":[171],"audio":[174,926,937,1211,1223,1239,1250,1257,1273,1293],"(apart":[179],"12":[181,753,936],"audio-only":[182,1080],"clips).":[183],"<strong>Distance":[184],"labels</strong>":[185],"(in":[186],"cm)":[187],"annotated":[191,287,683],"events,":[193,667],"instead":[194],"azimuth":[198],"elevation":[200],"only":[201],"labels.":[202],"Contrary":[203],"three":[206],"datasets":[208],"synthetic":[210,258],"TAU":[215,358,866,880],"Events":[218,224,230,491],"2019":[219],"(development/evaluation),":[220],"TAU-NIGENS":[221,227],"2020,":[225],"2021":[231,335],"associated":[232],"iterations":[235],"Challenge,":[239,1187],"STARS22-23":[241],"real":[246,298,324,472],"hence":[250],"it":[251,315],"avoids":[252],"some":[253,1018],"pitfalls":[256],"generation":[259],"scenes.":[261,325],"Some":[262],"such":[263,550,596],"key":[264],"properties":[265],"are:":[266],"are":[268,291,608,637,670,676,692,706,717,732,928,966],"based":[269],"on":[270,392,548,948],"combination":[272],"human":[274],"annotators":[275],"event":[278,289,514,964],"activity":[279],"optical":[281,696],"tracking":[282,697],"positions,":[285],"classes":[290,310,675,705,965,969,1021],"determined":[292],"composition":[295],"scenes,":[299],"density,":[301,659],"polyphony,":[302],"occurences":[303],"co-occurences":[305],"not":[312,545],"random,":[313],"follows":[316],"actions":[317],"interactions":[319],"participants":[321,1151],"first":[327],"round":[328,341],"was":[331,344],"between":[333,346],"September":[334],"January":[337],"2022.":[338],"A":[339,365,466,739,822],"second":[340,922],"November":[347],"2022":[348,492],"February":[350],"2023.<br>":[351],"Collection":[353],"data":[355,737,1199,1212,1224,1258,1274],"side":[359],"has":[360],"received":[361],"funding":[362],"Google.":[364],"demo":[366],"video":[367,932],"combining":[368],"modalities":[371],"can":[375,534,729,951],"be":[376,535,952],"found":[377,441,497,953],"here.":[378,498,1059,1101],"<strong>REPORT":[379],"&amp;":[380],"REFERENCE:</strong>":[381],"If":[382,1175],"you":[383,387],"use":[384,1196,1310],"this":[385,390,1055,1097],"could":[388],"cite":[389],"report":[391],"its":[393],"design,":[394],"capturing,":[395],"process:":[398],"Kazuki":[399,446],"Shimada,":[400,447],"Archontis":[401,444],"Politis,":[402,445],"Parthasaarathy":[403,448],"Sudarsanam,":[404,449],"Daniel":[405,452],"Krause,":[406,453],"Kengo":[407],"Uchida,":[408],"Sharath":[409,450],"Adavanne,":[410,451],"Aapo":[411],"Hakala,":[412],"Yuichiro":[413,454],"Koyama,":[414,455],"Naoya":[415,456],"Takahashi,":[416,418,457,459],"Shusuke":[417,458],"Tuomas":[419,462],"Virtanen,":[420],"Yuki":[421,460],"Mitsufuji":[422],"(2023).":[423],"<strong>STARSS23:":[424],"Audio-Visual":[426],"Dataset":[427],"Recordings":[430,607],"Real":[432],"Scenes":[433,489],"Spatiotemporal":[435],"Annotations":[436],"Events</strong>,<br>":[439],"here,":[442],"Mitsufuji,":[461],"Virtanen":[463],"(2022).":[464],"<strong>STARSS22:":[465],"spatiotemporal":[475],"events</strong>.":[479],"In":[480],"<em>Proceedings":[481],"Classification":[486],"Acoustic":[488],"Workshop":[493],"(DCASE2022)</em>,":[494],"Nancy,":[495],"France.":[496],"<strong>AIM:</strong>":[499],"STARSS22-23":[501],"suitable":[504],"training":[506,841,869],"machine-listening":[510],"models":[511],"detection":[515],"(SED),":[516],"general":[517],"source":[519,553,599],"localization":[520,554,600],"diverse":[522,574,580],"sounds":[523,666],"or":[524,601,1000],"signal-of-interest":[525],"localization,":[526],"joint":[528,1049],"sound-event-localization-and-detection":[529],"(SELD).":[530],"Additionally,":[531,1083],"used":[536,1148],"signal":[540],"processing":[541,590],"methods":[542,555,591],"that":[543],"do":[544],"necessarily":[546],"rely":[547],"training,":[549],"acoustic":[552,558,581],"multiple-source":[557],"tracking.":[559],"allows":[562,586],"performance":[566],"robustness":[568],"aforementioned":[571],"applications":[572],"types":[575],"sounds,":[577],"under":[579,1078,1120],"conditions.":[582],"Specifically":[583],"audiovisual":[589,598,602,1122],"dimension,":[595],"object":[603],"recognition.":[604],"<strong>SPECIFICATIONS:</strong>":[605],"General:":[606],"taken":[609],"sites.":[613],"Each":[614],"clip":[616],"part":[618],"session":[622,641],"happening":[623],"unique":[626,638,743],"room.":[627],"Groups":[628],"participants,":[630],"making":[632],"props,":[633],"scene":[635],"scenarios":[636],"each":[640],"(with":[642],"few":[644],"exceptions).":[645],"To":[646],"achieve":[647],"good":[648],"variability":[649],"efficiency":[651],"data,":[654],"terms":[656],"presence,":[658],"movement,":[660],"and/or":[661],"distribution":[663],"loosely":[671,971],"scripted.":[672],"13":[673,961],"identified":[677],"strongly":[682],"humans.":[685],"those":[689],"active":[690],"captured":[693,745,774,795,816,843,857,871,885],"an":[695,1084],"system.":[698],"out":[701],"considered":[707],"interference.":[709],"Occurrences":[710],"up":[712],"3":[714,1154],"simultaneous":[715],"fairly":[718],"common,":[719],"while":[720],"higher":[721],"numbers":[722],"overlapping":[724],"(up":[726],"5)":[728],"occur":[730],"but":[731],"rare.":[733],"Volume,":[734],"duration,":[735],"split:":[738],"total":[740,770,791,812],"16":[742,896],"recordings,":[748,933],"4":[749],"Tokyo":[751,776],"Tampere":[755,797],"(development":[756,777,798],"set).":[757],"70":[758],"clips":[760,781,802],"30":[762,848],"sec":[763,784,805],"~":[764,785,806],"5":[765,887],"min":[766,787,808],"durations,":[767,788,809],"time":[771,792,813],"~2hrs,":[773],"dataset).":[778,799,821],"98":[779],"40":[783,804,834],"9":[786],"~5.5hrs,":[794],"79":[800],"7":[807,873],"~3.5hrs,":[815],"both":[818,1238,1249,1292],"sites":[819],"(evaluation":[820],"training-testing":[823],"split":[824],"provided":[826,1058,1100],"reporting":[828],"results":[829,1193],"contributed":[836,850,864,878],"Sony":[838,852],"split,":[842,856,870,884],"2":[845,859],"(dev-train-sony).":[847],"testing":[855,883,1202],"(dev-test-sony).":[861],"50":[862],"(dev-train-tau).":[875],"48":[876],"(dev-test-tau).":[889],"Audio:":[890],"Sampling":[891],"rate:":[892],"24kHz.":[893],"Bit":[894],"depth:":[895],"bits.":[897],"Two":[898],"3-dimensional":[900],"formats:":[902],"(FOA)":[905],"tetrahedral":[907],"(MIC).":[910],"Video:":[911],"Video":[912,916,919],"360\u00b0":[913],"format:":[914],"equirectangular":[915],"resolution:":[917],"1920x960":[918],"frames":[920],"per":[921],"(fps):":[923],"29.97":[924],"All":[925],"accompanied":[929],"synchronised":[931],"apart":[934],"missing":[940],"videos":[941,1236,1290],"(<em>fold3_room21_mix001.wav":[942],"-":[943],"fold3_room21_mix012.wav</em>)":[944],"More":[945],"detailed":[946],"information":[947,1034],"included":[956],"README":[957,1037],"file.":[958,1038],"<strong>SOUND":[959],"CLASSES:</strong>":[960],"annotated.":[967],"follow":[970],"Audioset":[973],"ontology.":[974],"0.":[975],"<strong>Female":[976],"speech,":[977,982],"woman":[978],"speaking</strong><br>":[979,984],"1.":[980],"<strong>Male":[981],"man":[983],"2.":[985],"<strong>Clapping</strong><br>":[986],"3.":[987],"<strong>Telephone</strong><br>":[988],"4.":[989],"<strong>Laughter</strong><br>":[990],"5.":[991],"<strong>Domestic":[992],"sounds</strong><br>":[993],"6.":[994],"<strong>Walk,":[995],"footsteps</strong><br>":[996],"7.":[997],"<strong>Door,":[998],"open":[999],"close</strong><br>":[1001],"8.":[1002],"<strong>Music</strong><br>":[1003],"9.":[1004],"<strong>Musical":[1005],"instrument</strong><br>":[1006],"10.":[1007],"<strong>Water":[1008],"tap,":[1009],"faucet</strong><br>":[1010],"11.":[1011],"<strong>Bell</strong><br>":[1012],"12.":[1013],"<strong>Knock</strong>":[1014],"content":[1016],"these":[1020,1317],"corresponds":[1022,1255,1271],"limited":[1027],"range":[1028],"Audioset-related":[1030],"subclasses.":[1031],"For":[1032],"more":[1033],"see":[1035],"<strong>EXAMPLE":[1039],"APPLICATION:</strong>":[1040],"implementation":[1042,1061,1085,1103],"trainable":[1045,1088],"model":[1046,1089],"performing":[1047,1090],"<strong>audio-only</strong>":[1048],"SELD,":[1050,1092],"trained":[1051,1093],"evaluated":[1053,1095],"This":[1060,1102],"will":[1062,1104,1189],"baseline":[1066,1108],"method":[1067,1109],"Task,":[1077,1119],"inference":[1081,1123],"track.":[1082,1124],"<strong>audiovisual</strong>":[1091],"<strong>DEVELOPMENT":[1125],"AND":[1126],"EVALUATION:</strong>":[1127],"current":[1129],"(Version":[1131],"1.1)":[1132],"includes":[1136],"audio/video":[1138],"labels":[1141],"without":[1146],"labels,":[1147],"DCASE2023":[1156,1186],"Challenge":[1157],"train":[1159],"validate":[1161],"their":[1162,1180,1201],"submitted":[1163],"systems":[1164],"(development),":[1165],"produce":[1167],"system":[1168,1181],"outputs":[1169],"challenge":[1172],"phase.":[1174],"researchers":[1176],"wish":[1177],"compare":[1179],"against":[1182],"submissions":[1184],"they":[1188,1195],"have":[1190],"directly":[1191],"comparable":[1192],"if":[1194],"set.":[1203],"<strong>DOWNLOAD":[1204],"INSTRUCTIONS:</strong>":[1205],"file":[1207,1219,1231,1242,1253,1269,1285],"<strong><em>foa_dev.zip</em></strong>,":[1208],"correspond":[1209,1221],"<strong>FOA":[1215],"</strong>recording":[1216],"format.<br>":[1217],"<strong><em>mic_dev.zip</em></strong>,":[1220],"<strong>MIC</strong>":[1227,1277],"format.":[1229],"<strong><em>video_dev.zip":[1232],"</em></strong>contains":[1233],"common":[1235,1246,1289],"formats.<br>":[1240],"<strong><em>metadata_dev.zip</em></strong>":[1243],"metadata":[1247],"formats.":[1251],"<em><strong>foa_eval.zip</strong></em>":[1254],"<strong>FOA</strong>":[1261],"format":[1263,1279,1306],"dataset.<br>":[1267,1283],"<em><strong>mic_eval.zip</strong></em>":[1270],"<em><strong>video_eval.zip</strong></em>":[1286],"formats":[1294],"Download":[1299],"zip":[1301,1318],"files":[1302],"corresponding":[1303],"interest":[1308],"your":[1311],"favourite":[1312],"compression":[1313],"tool":[1314],"unzip":[1316],"files.":[1319]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}