{"id":"https://openalex.org/W6967978396","doi":"https://doi.org/10.5281/zenodo.15087603","title":"DCASE2025 Task3 Stereo SELD Dataset","display_name":"DCASE2025 Task3 Stereo SELD Dataset","publication_year":2025,"publication_date":"2025-04-01","ids":{"openalex":"https://openalex.org/W6967978396","doi":"https://doi.org/10.5281/zenodo.15087603"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.15087603","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15087603","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":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.15087603","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shimada, Kazuki","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":true,"raw_author_name":"Shimada, Kazuki","raw_affiliation_strings":["Sony AI"],"raw_orcid":"https://orcid.org/0000-0001-5389-2346","affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Politis, Archontis","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":false,"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":null,"display_name":"Roman, Iran R.","orcid":"https://orcid.org/0000-0003-3781-7244"},"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":"Roman, Iran R.","raw_affiliation_strings":["Queen Mary University of London"],"raw_orcid":"https://orcid.org/0000-0003-3781-7244","affiliations":[{"raw_affiliation_string":"Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sudarsanam, Parthasaarathy","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":"https://orcid.org/0009-0009-3751-6469","affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":null,"display_name":"D\u00edaz-Guerra Aparicio, David","orcid":"https://orcid.org/0000-0002-1041-0498"},"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":"D\u00edaz-Guerra Aparicio, David","raw_affiliation_strings":["Tampere University"],"raw_orcid":"https://orcid.org/0000-0002-1041-0498","affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pandey, Ruchi","orcid":"https://orcid.org/0009-0002-6627-2706"},"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":"Pandey, Ruchi","raw_affiliation_strings":["Tampere University"],"raw_orcid":"https://orcid.org/0009-0002-6627-2706","affiliations":[{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Uchida, Kengo","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 AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Koyama, Yuichiro","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 Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Takahashi, Naoya","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 AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shibuya, Takashi","orcid":"https://orcid.org/0000-0002-4277-0164"},"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":"Shibuya, Takashi","raw_affiliation_strings":["Sony AI"],"raw_orcid":"https://orcid.org/0000-0002-4277-0164","affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Takahashi, Shusuke","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 Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Virtanen, Tuomas","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"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mitsufuji, Yuki","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 AI","Sony Group Corporation"],"raw_orcid":"https://orcid.org/0000-0002-6806-6140","affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]},{"raw_affiliation_string":"Sony Group Corporation","institution_ids":["https://openalex.org/I2800278093"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":13,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2800278093"],"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":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.607699990272522},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5275999903678894},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5012000203132629},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3986000120639801},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3978999853134155},{"id":"https://openalex.org/keywords/stereophonic-sound","display_name":"Stereophonic sound","score":0.39660000801086426},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.3711000084877014}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7303000092506409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6819000244140625},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6365000009536743},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.607699990272522},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5275999903678894},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5012000203132629},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C140631703","wikidata":"https://www.wikidata.org/wiki/Q34678","display_name":"Stereophonic sound","level":3,"score":0.39660000801086426},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3711000084877014},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C2778739407","wikidata":"https://www.wikidata.org/wiki/Q165372","display_name":"CLIPS","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.25529998540878296},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.15087603","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15087603","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":"doi:10.5281/zenodo.15087603","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.15087603","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":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4393661452"],"related_works":[],"abstract_inverted_index":{"Description":[0],"The":[1,19,64,94,254,268,277,332,398,447,651,666,828,877,900,917,952,986,1044,1056,1078,1111,1144,1164],"DCASE2025":[2,62,110,333,423,1036,1066,1134,1160],"Task3":[3,111,334,424,1067],"Stereo":[4,112,335,425,795,1068],"SELD":[5,113,336,426,1046,1062,1069,1076],"Dataset":[6,337,427,1070],"is":[7,229,338,468,575,592,602,612,660,672,738,906,920,940,1020,1052],"a":[8,89,157,183,194,471,476,494,701,1008,1081,1105,1150],"stereo":[9,34,149,180,434,451,803,1045,1061,1096,1169],"audio":[10,25,35,143,150,178,435,442,452,618,878,1001,1088,1097,1170],"and":[11,26,36,56,76,81,99,120,144,151,214,320,342,362,367,394,405,416,437,443,453,485,505,559,570,636,679,914,949,957,974,988,996,1015,1040,1084,1109,1123,1138,1199],"video":[12,28,38,96,146,153,192,196,216,454,987,1091,1100],"dataset":[13,50,66,327,372,399,455,883,924,1051,1118,1146],"derived":[14,715,728],"from":[15,123,132,261,716,729,1071],"the":[16,48,52,61,103,109,117,124,133,140,162,169,175,190,198,203,207,215,238,250,282,285,290,297,302,305,310,371,403,408,422,450,460,503,527,608,631,663,691,712,725,744,753,763,773,783,832,881,885,904,912,923,930,945,964,967,971,992,1000,1028,1035,1065,1117,1127,1133,1154,1159,1173,1179,1183,1189,1192,1196],"STARSS23":[17,65,125,135,286,664],"dataset.":[18,126,746,1194],"original":[20,134,239],"STARSS23's":[21,240],"first-order":[22],"Ambisonics":[23],"(FOA)":[24],"360\u00b0":[27,95,145,606,1090],"data":[29,154,436,680,1047,1057,1171],"have":[30,991],"been":[31],"converted":[32],"to":[33,88,147,156,161,179,193,211,219,244,263,274,376,430,537,551,581,629,662,909,926,962,1094,1104,1136,1168,1205],"perspective":[37,152,195,306,1099,1180],"data,":[39],"simulating":[40],"regular":[41],"media":[42,233,444],"content.":[43,234],"These":[44],"clips":[45,131,640,696,713,726,1122],"serve":[46,1026],"as":[47,202,284,389,532,999,1027],"development":[49,745,882,1120,1174,1184,1193],"for":[51,313,340,347,411,490,512,740,752,762,772,782,922,1049,1172,1182,1191],"sound":[53,71,348,353,364,482,646,823],"event":[54,293,349,365,819,824],"localization":[55,355,366,392],"detection":[57,350,368],"(SELD)":[58],"task":[59],"of":[60,70,84,91,226,344,402,407,414,449,470,480,526,535,547,585,684,697,704,711,724,932,966,1007,1034,1116,1129,1132,1158],"Challenge.":[63,1161],"contains":[67,1178,1188],"multichannel":[68],"recordings":[69,504,619,692,717,730],"scenes":[72],"in":[73,232,304,316,440,459,475,502,690,718,731,749,759,769,779,880,895,898,1031],"various":[74],"rooms":[75,687,748,758,768,778],"environments,":[77],"together":[78],"with":[79,102,197,222,301,356,577,620,700,800,1017],"temporal":[80],"spatial":[82],"annotations":[83,511],"prominent":[85],"events":[86,515,524,540,549,647],"belonging":[87],"set":[90,206,633],"target":[92,498,528,645,822],"classes.":[93],"are":[97,258,271,280,488,500,516,530,541,556,626,714,727,751,761,771,781,960,977],"spatially":[98],"temporally":[100],"aligned":[101],"microphone":[104],"array":[105],"recordings.":[106,136],"To":[107,288],"construct":[108,1060],"Dataset,":[114],"we":[115,138,166,173,295],"conduct":[116],"following":[118],"sampling":[119,562,659],"conversion":[121],"procedures":[122],"We":[127,188,205,235],"first":[128,167],"sample":[129],"5-second":[130,141],"Then,":[137,172],"convert":[139,174,189],"FOA":[142,170,177,1075,1087],"generate":[148],"corresponding":[155],"fixed":[158,163,251],"point-of-view.":[159],"According":[160],"viewing":[164,200,252,571,600,610,947,955,972,1106],"angle,":[165,948,956],"rotate":[168,237],"audio.":[171,204],"rotated":[176],"audio,":[181],"emulating":[182],"mid-side":[184,797],"(M/S)":[185,798],"recording":[186,466,472,574,953],"technique.":[187],"equirectangular":[191],"same":[199,283,632,993],"angle":[201,601,611,894,973],"horizontal":[208,599],"field-of-view":[209],"(FOV)":[210],"100":[212],"degrees":[213],"resolution":[217],"(Width:Height)":[218],"640:360":[220],"pixels,":[221],"an":[223,519],"aspect":[224],"ratio":[225],"16:9,":[227],"which":[228],"widely":[230],"used":[231,375,907,1125],"also":[236,1053],"direction-of-arrival":[241],"(DOA)":[242],"labels":[243,247,257,270,279,300,1124],"new":[245,255,298,1095],"DOA":[246,299],"centered":[248],"at":[249,605,614,903,980],"angle.":[253,572,1107],"azimuth":[256],"folded":[259],"back":[260,262],"front,":[264],"considering":[265],"front-back":[266],"ambiguity.":[267,276],"elevation":[269],"omitted":[272],"due":[273],"top-bottom":[275],"distance":[278],"kept":[281,613],"one.":[287,665],"get":[289],"binary":[291],"onscreen/offscreen":[292,667],"labels,":[294],"compare":[296],"FOV":[303],"video.":[307],"Please":[308],"check":[309],"challenge":[311],"webpage":[312],"details":[314],"missing":[315,621],"this":[317,326,1018,1050],"description.":[318],"Report":[319],"reference":[321],"A":[322,573,589,598,682,735],"technical":[323],"report":[324],"about":[325],"will":[328,1025,1147],"be":[329,374,457,1148],"published.":[330],"Aim":[331],"suitable":[339],"training":[341,754,774,913],"evaluation":[343,401,1110,1145],"machine-listening":[345],"models":[346,432],"(SED),":[351],"general":[352],"source":[354,391],"diverse":[357,412,418],"sounds":[358,415,853],"or":[359,860,1073],"signal-of-interest":[360],"localization,":[361],"joint":[363,1012],"(SELD).":[369],"Additionally,":[370],"can":[373,456,553,1059],"evaluate":[377,431],"signal":[378],"processing":[379],"methods":[380,393],"that":[381,970],"do":[382,641],"not":[383,627,642,978],"necessarily":[384],"rely":[385],"on":[386],"training,":[387],"such":[388],"acoustic":[390,396,419],"multiple-source":[395],"tracking.":[397],"allows":[400,428],"performance":[404,931],"robustness":[406],"aforementioned":[409],"applications":[410],"types":[413],"under":[417,1038],"conditions.":[420,937],"Specifically,":[421],"us":[429],"using":[433,743],"explore":[438],"tasks":[439],"common":[441],"scenarios.":[445],"Specifications":[446],"specifications":[448],"summarized":[458],"following:":[461],"Recording":[462],"(STARSS22/23":[463],"setup):":[464],"Each":[465,561,938],"clip":[467,939,1082],"part":[469],"session":[473,492],"happening":[474],"unique":[477,489,686],"room.":[478],"Groups":[479],"participants,":[481],"making":[483],"props,":[484],"scene":[486],"scenarios":[487],"each":[491,596],"(with":[493],"few":[495,1151],"exceptions).":[496],"13":[497,821],"classes":[499,529,820,825,829],"identified":[501],"strongly":[506],"annotated":[507],"by":[508,518,942,1126],"humans.":[509],"Spatial":[510],"those":[513],"active":[514],"captured":[517,689],"optical":[520],"tracking":[521],"system.":[522],"Sound":[523,818],"out":[525],"considered":[531],"interference.":[533],"Occurrences":[534],"up":[536],"3":[538,1033,1131],"simultaneous":[539],"fairly":[542],"common,":[543],"while":[544,607],"higher":[545],"numbers":[546],"overlapping":[548],"(up":[550],"6)":[552],"occur":[554],"but":[555,983],"rare.":[557],"Sampling":[558,788],"conversion:":[560],"step":[563],"randomly":[564,943,1083],"selects":[565],"its":[566,1086],"recording,":[567,946],"start":[568,590,950,958,975],"frame,":[569],"selected":[576,593,603,628],"length-weighted":[578],"random":[579,649,658],"choice":[580],"treat":[582],"all":[583,586,655,670],"frames":[584,656,671,813],"files":[587,879,990,1198],"equally.":[588],"frame":[591],"uniformly":[594,604],"within":[595],"recording.":[597],"vertical":[609],"0\u00b0":[615],"elevation.":[616],"12":[617],"videos":[622,1181],"(fold3_room21_mix001.wav":[623],"-":[624],"fold3_room21_mix012.wav)":[625],"keep":[630],"between":[634,911],"audio-only":[635,1039],"audiovisual":[637,1041],"tracks.":[638,1043],"Several":[639],"contain":[643],"any":[644],"after":[648,657],"sampling.":[650],"class":[652],"distribution":[653,668],"across":[654,669],"similar":[661],"around":[673],"1":[674],":":[675],"3.":[676,847],"Volume,":[677],"duration,":[678,699],"split:":[681],"total":[683,702],"16":[685,793],"were":[688,826],"(development":[693,707,720,733],"set).":[694],"30,000":[695],"5-sec":[698],"time":[703,897,959,976],"41.7":[705],"hrs":[706],"dataset).":[708,721,734],"23.9":[709],"%":[710,723],"Tokyo":[719,750,760],"76.1":[722],"Tampere":[732,770,780],"training-testing":[736],"split":[737,755,765,775,785],"provided":[739,921,961,1021],"reporting":[741],"results":[742],"2":[747,757],"(dev-train-sony).":[756],"testing":[764,784,915],"(dev-test-sony).":[766],"7":[767],"(dev-train-tau).":[776],"5":[777],"(dev-test-tau).":[786],"Audio:":[787],"rate:":[789],"24kHz.":[790],"Bit":[791],"depth:":[792],"bits.":[794],"format:":[796,807],"technique":[799],"left-right":[801],"cardioid":[802],"patterns.":[804],"Video:":[805],"Video":[806,809,812],"perspective.":[808],"resolution:":[810],"640x360.":[811],"per":[814,892],"second":[815],"(fps):":[816],"29.97.":[817],"annotated.":[827],"follow":[830,884],"loosely":[831],"AudioSet":[833],"ontology.":[834],"0.":[835],"Female":[836],"speech,":[837,842],"woman":[838],"speaking":[839,844],"1.":[840],"Male":[841],"man":[843],"2.":[845],"Clapping":[846],"Telephone":[848],"4.":[849],"Laughter":[850],"5.":[851],"Domestic":[852],"6.":[854],"Walk,":[855],"footsteps":[856],"7.":[857],"Door,":[858],"open":[859],"close":[861],"8.":[862],"Music":[863],"9.":[864],"Musical":[865],"instrument":[866],"10.":[867],"Water":[868],"tap,":[869],"faucet":[870],"11.":[871],"Bell":[872],"12.":[873],"Knock":[874],"Naming":[875],"convention":[876,998],"naming":[886,997],"convention:":[887],"fold[fold":[888],"number]_room[room":[889],"number]_mix[recording":[890],"number":[891,902],"room]_deg[viewing":[893],"degree]_start[start":[896],"frame].wav":[899],"fold":[901],"moment":[905],"only":[908],"distinguish":[910],"split.":[916],"room":[918],"information":[919],"user":[925],"potentially":[927],"help":[928],"understand":[929],"their":[933,1140],"method":[934,1030],"concerning":[935],"different":[936],"generated":[941],"selecting":[944],"time.":[951],"number,":[954],"indicate":[963],"configuration":[965],"clip.":[968],"Note":[969],"sampled":[979,984],"equal":[981],"intervals":[982],"randomly.":[985],"metadata":[989,1093,1102,1190],"folder":[994],"structure":[995],"files.":[1002,1209],"Example":[1003],"application":[1004],"An":[1005],"implementation":[1006,1024],"trainable":[1009],"model":[1010],"performing":[1011],"SELD,":[1013],"trained":[1014],"evaluated":[1016],"dataset,":[1019],"here.":[1022,1055],"This":[1023],"baseline":[1029],"Task":[1032,1130],"Challenge":[1037,1135],"inference":[1042],"generator":[1048,1058,1079],"available":[1054],"datasets":[1063],"like":[1064],"real":[1072],"synthetic":[1074],"datasets.":[1077],"samples":[1080],"converts":[1085],"/":[1089,1092,1098,1101],"according":[1103],"Development":[1108],"current":[1112],"version":[1113],"(Version":[1114],"1.0.0)":[1115],"includes":[1119],"audio/video":[1121],"participants":[1128],"train":[1137],"validate":[1139],"submitted":[1141],"systems":[1142],"(development).":[1143],"released":[1149],"weeks":[1152],"before":[1153],"final":[1155],"submission":[1156],"deadline":[1157],"Download":[1162,1195],"instruction":[1163],"file":[1165,1176,1186],"stereo_dev.zip":[1166],"corresponds":[1167],"dataset.The":[1175,1185],"video_dev.zip":[1177],"metadata_dev.zip":[1187],"zip":[1197,1208],"use":[1200],"your":[1201],"favorite":[1202],"compression":[1203],"tool":[1204],"unzip":[1206],"these":[1207]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
