{"id":"https://openalex.org/W4393619266","doi":"https://doi.org/10.5281/zenodo.4060432","title":"FSD50K","display_name":"FSD50K","publication_year":2020,"publication_date":"2020-10-02","ids":{"openalex":"https://openalex.org/W4393619266","doi":"https://doi.org/10.5281/zenodo.4060432"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:4060432","is_oa":true,"landing_page_url":"https://zenodo.org/record/4060432","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/4060432","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025025113","display_name":"Eduardo Fonseca","orcid":"https://orcid.org/0000-0001-9872-3917"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Fonseca, Eduardo","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":"https://orcid.org/0000-0001-9872-3917","affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066100176","display_name":"Xavier Favory","orcid":"https://orcid.org/0000-0001-6148-0018"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Favory, Xavier","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103137809","display_name":"Jordi Pons","orcid":"https://orcid.org/0000-0001-9603-0869"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pons, Jordi","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072565954","display_name":"Frederic Font","orcid":"https://orcid.org/0000-0002-4360-3210"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Font, Frederic","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":"https://orcid.org/0000-0002-4360-3210","affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Serra, Xavier","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona"],"raw_orcid":"https://orcid.org/0000-0003-1395-2345","affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"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":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.39505645632743835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.39505645632743835}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:4060432","is_oa":true,"landing_page_url":"https://zenodo.org/record/4060432","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"dataset"},{"id":"doi:10.5281/zenodo.4060432","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4060432","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:4060432","is_oa":true,"landing_page_url":"https://zenodo.org/record/4060432","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":"dataset"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G972256834","display_name":"Audio Commons: An Ecosystem for Creative Reuse of Audio Content","funder_award_id":"688382","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"FSD50K":[0,23,41,138,248,305,647,672,787,804,879,888,910,927,999,1071,1360],"is":[1,166,173,225,263,343,492,586,594,631,791,805,811,837,1109,1209],"an":[2,58,226,530,801,1074],"open":[3,59,227],"dataset":[4,60,228,319,453,833,1059,1072],"of":[5,32,45,61,105,114,127,130,143,149,229,257,267,315,336,346,361,403,414,421,469,472,508,554,572,605,610,621,695,714,734,757,794,828,857,878,934,994,1069,1082,1147,1163,1225,1243,1272,1288,1317,1352],"human-labeled":[6,62,230],"sound":[7,63,231,322,347,352,416,459,498,511,996,1014,1308],"events":[8,232,348],"containing":[9,233],"51,197":[10,234,307],"Freesound":[11,218,235,397,422,501,544,1111,1116,1344],"clips":[12,236,309,428,486,521,540,550,617,670,716,736,770,946,954,1025,1035,1327,1339],"unequally":[13,237],"distributed":[14,238],"in":[15,100,133,175,239,375,479,565,646,650,671,692,779,813,861,874,908,947,955,998,1105,1140,1160,1177,1200,1228,1262,1358],"200":[16,240,321,995,1270],"classes":[17,241,323,417,645,997,1015,1271],"drawn":[18,242],"from":[19,53,168,243,310,406,541,767],"the":[20,28,40,103,119,128,244,253,284,337,396,412,415,419,447,542,566,570,573,640,689,718,738,768,780,792,814,819,826,832,938,948,956,974,985,1013,1023,1033,1050,1070,1085,1089,1093,1097,1102,1110,1121,1125,1135,1141,1145,1148,1153,1167,1172,1178,1184,1196,1203,1223,1244,1254,1259,1269,1275,1296,1315,1318,1343,1359,1381,1390],"AudioSet":[21,245,338,1179,1221,1256,1276],"Ontology.":[22,339],"has":[24,97,249,384,682,800],"been":[25,98,250,385,1138],"created":[26,251],"at":[27,102,214,252,276,446,899,922],"Music":[29,254],"Technology":[30,255],"Group":[31,256],"Universitat":[33,258],"Pompeu":[34,259],"Fabra.":[35,260],"<strong>Citation</strong>":[36],"If":[37,590,883],"you":[38,210,905,1063],"use":[39,887,1115,1215,1240],"dataset,":[42],"or":[43,852,1189],"part":[44],"it,":[46],"please":[47,892,915],"cite":[48],"our":[49,277,480,611,1164],"TASLP":[50,101],"paper":[51,96,278,1192],"(available":[52],"[arXiv]":[54],"[TASLP]):":[55],"<pre>@article{fonseca2022FSD50K,":[56],"title={{FSD50K}:":[57],"events},":[64],"author={Fonseca,":[65],"Eduardo":[66,182,207,894,917],"and":[67,70,73,76,84,139,152,198,301,327,354,368,418,467,487,503,510,529,602,637,662,703,753,783,798,896,901,919,924,1266,1274,1290,1310,1324,1373,1380],"Favory,":[68,185],"Xavier":[69,184],"Pons,":[71,187],"Jordi":[72,186],"Font,":[74],"Frederic":[75,897,920],"Serra,":[77],"Xavier},":[78],"journal={IEEE/ACM":[79],"Transactions":[80],"on":[81,1195],"Audio,":[82],"Speech,":[83],"Language":[85],"Processing},":[86],"volume={30},":[87],"pages={829--852},":[88],"year={2022},":[89],"publisher={IEEE}":[90],"}":[91],"</pre>":[92,1076],"<em>Paper":[93],"update</em>:":[94],"This":[95,809,1107],"published":[99],"beginning":[104],"2022.":[106],"The":[107,122,162,318,340,370,381,452,519,710,730,775,855,1058],"accepted":[108],"camera-ready":[109,164],"version":[110,165],"includes":[111],"a":[112,264,274,334,391,456,470,506,525,591,765,789,795,835,858,872,932,1216,1286,1334,1394],"number":[113,1108],"improvements":[115],"with":[116,289,333,717,737,818,844,871,937,1234,1280,1292],"respect":[117],"to":[118,158,205,282,408,411,484,569,699,754,760,771,886,1101,1144,1171,1187,1230,1253,1306,1329,1369],"initial":[120],"submission.":[121],"main":[123],"updates":[124],"include:":[125],"estimation":[126],"amount":[129],"label":[131,1154,1265],"noise":[132],"FSD50K,":[134,1293],"SNR":[135],"comparison":[136],"between":[137],"AudioSet,":[140,651],"improved":[141],"description":[142,1060],"evaluation":[144,468,531,731],"metrics":[145],"including":[146,357],"equations,":[147],"clarification":[148],"experimental":[150],"methodology":[151],"some":[153,155,694,704,1351],"results,":[154],"content":[156,342],"moved":[157],"Appendix":[159,1161],"for":[160,223,292,600,639,831,880,889,911,962,973,984,1003,1049,1193,1222,1268],"readability.":[161],"TASLP-accepted":[163],"available":[167,494],"arXiv":[169],"(in":[170],"particular,":[171],"it":[172,596,799,841],"v2":[174],"arXiv,":[176],"displayed":[177],"by":[178,350,388,688,869,1342,1389],"default).":[179],"<strong>Data":[180],"curators</strong>":[181],"Fonseca,":[183],"Mercedes":[188],"Collado,":[189],"Ceren":[190],"Can,":[191],"Rachit":[192],"Gupta,":[193],"Javier":[194],"Arredondo,":[195],"Gary":[196],"Avendano":[197],"Sara":[199],"Fernandez":[200],"<strong>Contact</strong>":[201],"You":[202,1249],"are":[203,402,429,444,522,576,635,648,673,777,906,1064,1132,1340,1355,1387],"welcome":[204],"contact":[206,893,916],"Fonseca":[208,895,918],"should":[209,597],"have":[211,273,539,1137],"any":[212],"questions,":[213],"efonseca@google.com.":[215],"<strong>ABOUT":[216],"FSD50K</strong>":[217],"Dataset":[219],"50k":[220],"(or":[221],"<strong>FSD50K</strong>":[222],"short)":[224],"Ontology":[246,1180,1277],"[1].":[247],"What":[261],"follows":[262],"brief":[265],"summary":[266],"FSD50K's":[268,963],"most":[269],"important":[270],"characteristics.":[271],"Please":[272],"look":[275],"(especially":[279],"Section":[280],"4)":[281],"extend":[283],"basic":[285],"information":[286,1260],"provided":[287,430,445,587,1261,1388],"here":[288],"relevant":[290],"details":[291,1151,1194],"its":[293,683],"usage,":[294],"as":[295,297,431,686,788,834,840,848,931,1073,1118,1175,1333],"well":[296],"discussion,":[298],"limitations,":[299],"applications":[300],"more.":[302,369],"<strong>Basic":[303],"characteristics:</strong>":[304],"contains":[306,1084],"audio":[308,317,341,439,485,520,549,555,616,622,669,769,849,1080,1322],"Freesound,":[311,693],"totalling":[312,551,618],"108.3":[313],"hours":[314,553,620],"multi-labeled":[316],"encompasses":[320],"(144":[324],"leaf":[325],"nodes":[326],"56":[328],"intermediate":[329],"nodes)":[330],"hierarchically":[331],"organized":[332],"subset":[335],"composed":[344],"mainly":[345,455],"produced":[349],"physical":[351],"sources":[353],"production":[355],"mechanisms,":[356],"human":[358],"sounds,":[359,365,664],"sounds":[360],"things,":[362],"animals,":[363],"natural":[364],"musical":[366],"instruments":[367],"vocabulary":[371],"can":[372,928,1157,1250],"be":[373,580,598,929,1158,1349],"inspected":[374],"<code>vocabulary.csv</code>":[376,1263],"(see":[377,476,515,607,1191],"Files":[378,516,961,1002,1048],"section":[379,517],"below).":[380,518],"acoustic":[382],"material":[383],"manually":[386],"labeled":[387,632],"humans":[389],"following":[390,719,739,939,1086,1297],"data":[392,853],"labeling":[393],"process":[394,797,1156],"using":[395,909,1258],"Annotator":[398],"platform":[399],"[2].":[400],"Clips":[401],"variable":[404],"length":[405],"0.3":[407],"30s,":[409],"due":[410],"diversity":[413],"preferences":[420],"users":[423],"when":[424],"recording":[425],"sounds.":[426],"All":[427,644,668,1384],"uncompressed":[432],"PCM":[433],"16":[434],"bit":[435],"44.1":[436],"kHz":[437],"mono":[438],"files.":[440],"Ground":[441,971,982],"truth":[442,965,972,983],"labels":[443,561,563,628,1123,1131,1136,1227],"clip-level":[448],"(i.e.,":[449,562,1124],"weak":[450],"labels).":[451],"poses":[454],"large-vocabulary":[457],"multi-label":[458],"event":[460,512],"classification":[461],"problem,":[462],"but":[463,578],"also":[464],"allows":[465],"development":[466,526,711],"variety":[471,507,1287],"machine":[473,912],"listening":[474],"approaches":[475,1291],"Sec.":[477,608],"4D":[478],"paper).":[481],"In":[482,785],"addition":[483],"ground":[488,964,1126],"truth,":[489],"additional":[490,802,1004,1281],"metadata":[491,1005,1282,1386],"made":[493],"(including":[495],"raw":[496],"annotations,":[497,851],"predominance":[499],"ratings,":[500],"metadata,":[502],"more),":[504],"allowing":[505],"analyses":[509],"research":[513],"tasks":[514],"grouped":[523],"into":[524],"(<em>dev</em>)":[527],"set":[528,533,630,712,732,950,958,976,987],"(<em>eval</em>)":[532],"such":[534],"that":[535,825,1062,1207,1350],"they":[536],"do":[537],"not":[538,838,1356],"same":[543,1204,1393],"uploader.":[545,1391],"<strong>Dev":[546],"set:</strong>":[547,614],"40,966":[548,715],"80.4":[552],"Avg":[556,623],"duration/clip:":[557,624],"7.1s":[558],"114,271":[559],"smeared":[560,627],"propagated":[564,1139],"upwards":[567,1142],"direction":[568,1143],"root":[571,1146],"ontology)":[574],"Labels":[575],"correct":[577,636],"could":[579],"occasionally":[581],"incomplete":[582],"A":[583],"train/validation":[584],"split":[585,593],"(Sec.":[588],"3H).":[589],"different":[592,845,1218],"used,":[595],"specified":[599,778,812],"reproducibility":[601],"fair":[603],"comparability":[604],"results":[606],"5C":[609],"paper)":[612],"<strong>Eval":[613],"10,231":[615,735],"27.9":[619],"9.8s":[625],"38,596":[626],"Eval":[629],"exhaustively":[633],"(labels":[634],"complete":[638],"considered":[641],"vocabulary)":[642],"<strong>Note:</strong>":[643,1213,1346],"represented":[649],"except":[652,1206],"<code>Crash":[653],"cymbal</code>,":[654],"<code>Human":[655,658],"group":[656],"actions</code>,":[657],"voice</code>,":[659],"<code>Respiratory":[660],"sounds</code>,":[661],"<code>Domestic":[663],"home":[665],"sounds</code>.":[666],"<strong>LICENSE</strong>":[667],"released":[674,806],"under":[675,807],"Creative":[676],"Commons":[677],"(CC)":[678],"licenses.":[679,774],"Each":[680,1077],"clip":[681,690,1185,1372,1378],"own":[684],"license":[685,810,830,860],"defined":[687,1176],"uploader":[691,1382],"them":[696],"requiring":[697],"attribution":[698,751,756],"their":[700,772],"original":[701,1245,1255],"authors":[702],"forbidding":[705],"further":[706,866],"commercial":[707,881,890],"reuse.":[708],"Specifically:":[709],"consists":[713,733],"licenses:":[720,740],"CC0:":[721,741],"14,959":[722],"CC-BY:":[723,743],"20,017":[724],"CC-BY-NC:":[725,745],"4616":[726],"CC":[727,747],"Sampling+:":[728,748],"1374":[729],"4914":[742],"3489":[744],"1425":[746],"403":[749],"For":[750],"purposes":[752],"facilitate":[755],"these":[758,862,1129,1353,1385],"files":[759,781,936],"third":[761],"parties,":[762],"we":[763,1239,1294],"include":[764],"mapping":[766],"corresponding":[773,1170],"licenses":[776,846],"<code>dev_clips_info_FSD50K.json</code>":[782],"<code>eval_clips_info_FSD50K.json</code>.":[784],"addition,":[786],"whole":[790,836],"result":[793],"curation":[796],"license:":[803],"CC-BY.":[808],"<code>LICENSE-DATASET</code>":[815],"file":[816,1061,1090,1103],"downloaded":[817,930],"<code>FSD50K.doc</code>":[820],"zip":[821,935],"file.":[822],"We":[823,1113,1214],"note":[824],"choice":[827,856],"one":[829,1307,1370],"straightforward":[839],"comprises":[842],"items":[843],"(such":[847],"clips,":[850],"split).":[854],"global":[859],"cases":[863],"may":[864,1348],"warrant":[865],"investigation":[867],"(e.g.,":[868],"someone":[870],"background":[873],"copyright":[875],"law).":[876],"<strong>Usage":[877],"purposes:</strong>":[882],"you'd":[884],"like":[885],"purposes,":[891],"Font":[898,921],"efonseca@google.com":[900,923],"frederic.font@upf.edu.":[902,925],"Also,":[903],"if":[904],"interested":[907],"learning":[913],"competitions,":[914],"<strong>FILES</strong>":[926],"series":[933],"directory":[940],"structure:":[941],"<pre>root":[942],"\u2502":[943,951,959,966,967,968,977,978,979,988,989,990,1000,1006,1007,1008,1016,1017,1018,1026,1027,1028,1036,1037,1038,1043,1044,1045,1054,1056,1066],"\u2514\u2500\u2500\u2500FSD50K.dev_audio/":[944],"Audio":[945,953,1338],"dev":[949,975,1024,1371],"\u2514\u2500\u2500\u2500FSD50K.eval_audio/":[952],"eval":[957,986,1034],"\u2514\u2500\u2500\u2500FSD50K.ground_truth/":[960],"\u2514\u2500\u2500\u2500":[969,980,991,1009,1019,1029,1039,1046],"dev.csv":[970],"eval.csv":[981],"vocabulary.csv":[992],"List":[993],"\u2514\u2500\u2500\u2500FSD50K.metadata/":[1001],"class_info_FSD50K.json":[1010],"Metadata":[1011,1021,1031],"about":[1012,1022,1032,1152],"dev_clips_info_FSD50K.json":[1020],"eval_clips_info_FSD50K.json":[1030],"pp_pnp_ratings_FSD50K.json":[1040],"PP/PNP":[1041],"ratings":[1042],"collection/":[1047],"*sound":[1051],"collection*":[1052],"format":[1053,1219],"\u2514\u2500\u2500\u2500FSD50K.doc/":[1055],"\u2514\u2500\u2500\u2500README.md":[1057],"reading":[1065],"\u2514\u2500\u2500\u2500LICENSE-DATASET":[1067],"License":[1068],"entity":[1075],"row":[1078],"(i.e.":[1079],"clip)":[1081],"<code>dev.csv</code>":[1083],"information:":[1087],"<code>fname</code>:":[1088],"name":[1091],"without":[1092],"<code>.wav</code>":[1094],"extension,":[1095],"e.g.,":[1096],"fname":[1098],"<code>64760</code>":[1099],"corresponds":[1100,1305,1368],"<code>64760.wav</code>":[1104],"disk.":[1106],"id.":[1112,1345],"always":[1114],"ids":[1117],"filenames.":[1119],"<code>labels</code>:":[1120],"class":[1122,1130,1173,1226,1309],"truth).":[1127],"Note":[1128],"<em>smeared</em>,":[1133],"i.e.,":[1134],"ontology.":[1149],"More":[1150],"smearing":[1155],"found":[1159],"D":[1162],"paper.":[1165],"<code>mids</code>:":[1166],"Freebase":[1168],"identifiers":[1169],"labels,":[1174],"specification":[1181],"<code>split</code>:":[1182],"whether":[1183],"belongs":[1186],"<em>train</em>":[1188],"<em>val</em>":[1190],"proposed":[1197],"split)":[1198],"Rows":[1199],"<code>eval.csv</code>":[1201],"follow":[1202],"format,":[1205],"there":[1208],"no":[1210],"<code>split</code>":[1211],"column.":[1212],"slightly":[1217],"than":[1220],"naming":[1224,1257],"order":[1229],"avoid":[1231],"potential":[1232],"problems":[1233],"spaces,":[1235],"commas,":[1236],"etc.":[1237],"Example:":[1238],"<code>Accelerating_and_revving_and_vroom</code>":[1241],"instead":[1242],"<code>Accelerating,":[1246],"revving,":[1247],"vroom</code>.":[1248],"go":[1251],"back":[1252],"(class":[1264],"mid":[1267],"FSD50K)":[1273],"specification.":[1278],"<strong>Files":[1279],"(FSD50K.metadata/)</strong>":[1283],"To":[1284],"allow":[1285],"analysis":[1289],"provide":[1295],"metadata:":[1298],"<code>class_info_FSD50K.json</code>:":[1299],"python":[1300,1363],"dictionary":[1301,1364],"where":[1302,1365],"each":[1303,1366],"entry":[1304,1367],"contains:":[1311,1374],"<code>FAQs</code>":[1312],"utilized":[1313],"during":[1314,1331],"annotation":[1316,1332],"class,":[1319],"<code>examples</code>":[1320],"(representative":[1321],"clips),":[1323],"<code>verification_examples</code>":[1325],"(audio":[1326],"presented":[1328],"raters":[1330],"quality":[1335],"control":[1336],"mechanism).":[1337],"described":[1341],"It":[1347],"examples":[1354],"included":[1357],"release.":[1361],"<code>dev_clips_info_FSD50K.json</code>:":[1362],"title,":[1375],"description,":[1376],"tags,":[1377],"license,":[1379],"name.":[1383],"<code>eval_clips_info_FSD50K.json</code>:":[1392]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2024-04-03T00:00:00"}