{"id":"https://openalex.org/W4393729646","doi":"https://doi.org/10.5281/zenodo.4642005","title":"L3DAS21 Challenge","display_name":"L3DAS21 Challenge","publication_year":2021,"publication_date":"2021-03-27","ids":{"openalex":"https://openalex.org/W4393729646","doi":"https://doi.org/10.5281/zenodo.4642005"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:4642005","is_oa":true,"landing_page_url":"https://zenodo.org/record/4642005","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":"dataset"},"type":"dataset","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/4642005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019647783","display_name":"Danilo Comminiello","orcid":"https://orcid.org/0000-0003-4067-4504"},"institutions":[{"id":"https://openalex.org/I4210099865","display_name":"European University of Rome","ror":"https://ror.org/011at3t25","country_code":"IT","type":"education","lineage":["https://openalex.org/I4210099865"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Danilo Comminiello","raw_affiliation_strings":["University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rome","institution_ids":["https://openalex.org/I4210099865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014462103","display_name":"Eric Guizzo","orcid":"https://orcid.org/0000-0002-2857-4140"},"institutions":[{"id":"https://openalex.org/I4210099865","display_name":"European University of Rome","ror":"https://ror.org/011at3t25","country_code":"IT","type":"education","lineage":["https://openalex.org/I4210099865"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Eric Guizzo","raw_affiliation_strings":["University of Rome"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rome","institution_ids":["https://openalex.org/I4210099865"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210099865"],"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/T11309","display_name":"Music and Audio Processing","score":0.6209999918937683,"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":0.6209999918937683,"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":0.3093000054359436,"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":0.02239999920129776,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.29172733426094055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.29172733426094055}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:zenodo.org:4642005","is_oa":true,"landing_page_url":"https://zenodo.org/record/4642005","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":"dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:4642005","is_oa":true,"landing_page_url":"https://zenodo.org/record/4642005","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":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"L3DAS21:":[0],"MACHINE":[1],"LEARNING":[2],"FOR":[3],"3D":[4,33,96,100,160,197,224,394,414,452,461,506,525],"AUDIO":[5],"SIGNAL":[6],"PROCESSING\\n\\nIEEE":[7],"MLSP":[8,21,706],"Data":[9],"Challenge":[10,17,92,700],"2021\\n\\n":[11],"\\n\\nSCOPE":[12],"OF":[13],"THE":[14],"CHALLENGE\\n\\nThe":[15],"L3DAS21":[16,91,157],"for":[18,32,74,205,451,489,560,600,605,613,618],"the":[19,47,57,61,64,152,156,168,175,185,191,196,212,237,256,258,265,287,293,311,325,328,335,345,365,376,384,412,426,432,444,494,505,541,547,568,574,578,588,630,647,653,662,675],"IEEE":[20],"2021":[22],"aims":[23],"at":[24,72,273,389,540],"encouraging":[25],"and":[26,53,67,99,104,122,133,217,228,269,295,303,330,379,392,404,425,455,510,513,570,577,602,607,615,639,641],"fostering":[27],"research":[28],"on":[29,108,280,344],"machine":[30],"learning":[31],"audio":[34,307,462,517,527],"signal":[35,66,194,337],"processing.":[36],"In":[37,471,544],"multi-speaker":[38],"scenarios":[39,395],"it":[40,71],"is":[41,60,167,208,234,435,449,477,502,633],"very":[42],"important":[43],"to":[44,69,189,235,251,286,357,396,431,443,468,504,532,552,622,656,674],"properly":[45],"understand":[46],"nature":[48],"of":[49,63,137,143,151,155,164,170,179,211,231,240,244,264,276,314,327,407,567,581,629,650,661,678],"a":[50,75,180,209,241,262,315,332,465,474,523,554,565,595,608],"sound":[51,65,177,245,267,361,403,584],"event":[52,246,585],"its":[54],"position":[55],"within":[56],"environment,":[58],"what":[59],"content":[62],"how":[68],"leverage":[70],"best":[73],"specific":[76],"application":[77],"(e.g.,":[78],"teleconferencing":[79],"rather":[80],"than":[81,458],"assistive":[82],"listening":[83],"or":[84],"entertainment,":[85],"among":[86],"others).":[87],"To":[88],"this":[89,165,206,232,281,490,545,561],"end,":[90],"presents":[93],"two":[94,138,144,320,438,636],"tasks:":[95],"Speech":[97,161,453],"Enhancement":[98,454],"Sound":[101,225,507],"Event":[102,226,508],"Localization":[103,227,509],"Detection,":[105],"both":[106,591],"relying":[107],"first-order":[109,145,321],"Ambisonics":[110,131,139,146,306,322,347],"recordings":[111],"in":[112,174,249,255,324,338,401,411,437,529,587,635],"reverberant":[113,181,415],"office":[114,182,317,526],"environment.\\n\\nEach":[115],"task":[116,166,207,233,282,512],"involves":[117],"2":[118,685],"separate":[119],"tracks:":[120],"1-mic":[121],"2-mic":[123],"recordings,":[124],"respectively":[125,441],"containing":[126,199],"sounds":[127,367],"acquired":[128],"by":[129,134,363],"one":[130,150],"microphone":[132],"an":[135],"array":[136],"microphones.":[140],"The":[141,626],"use":[142],"microphones":[147,323],"definitely":[148],"represents":[149],"main":[153,439],"novelties":[154],"Challenge.\\n\\n\\n\\tTask":[158],"1:":[159],"Enhancement\\n\\tThe":[162],"objective":[163,214],"enhancement":[169],"speech":[171,373,643],"signals":[172,374],"immersed":[173],"spatial":[176,341,579],"field":[178,313],"environment.":[183,416],"Here":[184],"models":[186,259],"are":[187,283,549,665,683],"expected":[188],"extract":[190],"monophonic":[192,355,496],"voice":[193,476,497],"from":[195,375,383,646],"mixture":[198],"various":[200],"background":[201,381,408,484],"noises.The":[202],"evaluation":[203,689],"metric":[204],"combination":[210],"short-time":[213],"intelligibility":[215],"(STOI)":[216],"word":[218],"error":[219],"rate":[220],"(WER).\\n\\t":[221],"\\n\\tTask":[222],"2:":[223],"Detection\\n\\tThe":[229],"aim":[230],"detect":[236],"temporal":[238],"activities":[239],"known":[242],"set":[243,597,610,628],"classes":[247],"and,":[248],"particular,":[250],"further":[252],"locate":[253],"them":[254],"space.Here":[257],"must":[260],"predict":[261],"list":[263,566],"active":[266,539],"events":[268,536],"their":[270],"respective":[271],"location":[272],"regular":[274],"intervals":[275],"100":[277],"milliseconds.":[278],"Performance":[279],"evaluated":[284],"according":[285,430],"location-sensitive":[288],"detection":[289,296],"error,":[290],"which":[291,402,530,682],"joins":[292],"localization":[294],"errors.\\n\\n\\n":[297],"\\n\\nDATASETS\\n\\nThe":[298],"LEDAS21":[299],"datasets":[300,356,691],"contain":[301,553,642],"multiple-source":[302],"multiple-perspective":[304],"B-format":[305],"recordings.":[308],"We":[309,371,387,417],"sampled":[310],"acoustic":[312,535],"large":[316],"room,":[318],"placing":[319],"center":[326],"room":[329],"moving":[331],"speaker":[333],"reproducing":[334],"analytic":[336],"252":[339],"fixed":[340],"positions.":[342],"Relying":[343],"collected":[346],"impulse":[348],"responses":[349],"(IRs),":[350],"we":[351,492,563],"augmented":[352],"existing":[353],"clean":[354,495],"obtain":[358],"synthetic":[359],"tridimensional":[360],"sources":[362],"convolving":[364],"original":[366],"with":[368,464,481],"our":[369],"IRs.":[370],"extracted":[372,645],"Librispeech":[377,651],"dataset":[378,434,592],"office-like":[380,483],"noises":[382,409],"FSD50K":[385],"dataset.":[386],"aimed":[388],"creating":[390],"plausible":[391],"variegate":[393],"reflect":[397],"possible":[398,679],"real-life":[399],"situations":[400],"disparate":[405],"types":[406],"coexist":[410],"same":[413,542],"provide":[418,493,564],"normalized":[419],"raw":[420],"waveforms":[421],"as":[422],"predictors":[423],"data":[424,428,488,520,559],"target":[427,487,558],"varies":[429],"task.\\n\\nThe":[433],"divided":[436,634,666],"sections,":[440,500],"dedicated":[442,503],"challenge":[445],"tasks.\\n\\nThe":[446],"first":[447],"section":[448,491,562,632,664],"optimized":[450],"contains":[456,514,522],"more":[457],"30000":[459],"virtual":[460],"environments":[463],"duration":[466],"up":[467,531,655],"10":[469,657],"seconds.":[470],"each":[472,582],"sample,":[473],"spoken":[475,555],"always":[478],"present":[479,586],"alongside":[480],"other":[482,499],"noises.":[485],"As":[486,557],"signals.\\n\\nThe":[498],"instead,":[501],"Detection":[511],"900":[515],"60-seconds-long":[516],"files":[518],"Each":[519],"point":[521],"simulated":[524],"environment":[528],"3":[533],"simultaneous":[534],"may":[537],"be":[538,693],"time.":[543],"section,":[546],"samples":[548,644],"not":[550],"forced":[551],"voice.":[556],"onset":[569],"offset":[571],"time":[572],"stamps,":[573],"typology":[575],"class,":[576],"coordinates":[580],"individual":[583],"data-points.\\n\\nWe":[589],"split":[590],"sections":[593],"into:":[594],"training":[596],"(44":[598],"hours":[599,604,612,617],"SE":[601,614,631],"600":[603],"SELD)":[606],"test":[609,690],"(6":[611],"5":[616],"SELD),":[619],"paying":[620],"attention":[621],"create":[623],"similar":[624],"distributions.":[625],"train":[627],"partitions:":[637],"train360":[638],"train100,":[640],"correspondent":[648],"partitions":[649,672],"(only":[652],"sample)":[654],"seconds).":[658],"All":[659],"sets":[660],"SELD":[663],"in:":[667],"OV1,":[668],"OV2,":[669],"OV3.":[670],"These":[671],"refer":[673],"maximum":[676],"amount":[677],"overlapping":[680],"sounds,":[681],"1,":[684],"ore":[686],"3,":[687],"respectively.\\n\\nThe":[688],"can":[692],"downloaded":[694],"here:\\n\\n\\n\\tL3DAS21_Task1_test.zip\\n\\tL3DAS21_Task2_test.zip\\n\\n\\n":[695],"\\n\\nCHALLENGE":[696],"WEBSITE":[697],"AND":[698],"CONTACTS\\n\\nL3DAS21":[699],"Website:":[701],"www.l3das.com/mlsp2021\\n\\nGitHub":[702],"repository:":[703],"github.com/l3das/L3DAS21\\n\\nPaper:":[704],"arxiv.org/abs/2104.05499\\n\\nIEEE":[705],"2021:":[707],"2021.ieeemlsp.org/\\n\\nEmail":[708],"contact:":[709],"l3das@uniroma1.it\\n\\nTwitter:":[710],"https://twitter.com/das_l3":[711]},"counts_by_year":[],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2024-04-03T00:00:00"}