{"id":"https://openalex.org/W4391828784","doi":"https://doi.org/10.1109/icassp49357.2023.10433925","title":"Overview of the L3DAS23 Challenge on Audio-Visual Extended Reality","display_name":"Overview of the L3DAS23 Challenge on Audio-Visual Extended Reality","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4391828784","doi":"https://doi.org/10.1109/icassp49357.2023.10433925"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10433925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10433925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106469480","display_name":"C. Marinoni","orcid":"https://orcid.org/0009-0003-3716-7103"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Christian Marinoni","raw_affiliation_strings":["Sapienza University of Rome,DIET Dept.,Italy","DIET Dept., Sapienza University of Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,DIET Dept.,Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"DIET Dept., Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046834719","display_name":"Riccardo Fosco Gramaccioni","orcid":"https://orcid.org/0009-0003-1398-1880"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Riccardo F. Gramaccioni","raw_affiliation_strings":["Sapienza University of Rome,DIET Dept.,Italy","DIET Dept., Sapienza University of Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,DIET Dept.,Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"DIET Dept., Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054262111","display_name":"Changan Chen","orcid":"https://orcid.org/0009-0002-2926-5419"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changan Chen","raw_affiliation_strings":["UT Austin,TX,USA","UT Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UT Austin,TX,USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"UT Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039283820","display_name":"Aurelio Uncini","orcid":"https://orcid.org/0000-0002-5793-0917"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Aurelio Uncini","raw_affiliation_strings":["Sapienza University of Rome,DIET Dept.,Italy","DIET Dept., Sapienza University of Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,DIET Dept.,Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"DIET Dept., Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019647783","display_name":"Danilo Comminiello","orcid":"https://orcid.org/0000-0003-4067-4504"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Danilo Comminiello","raw_affiliation_strings":["Sapienza University of Rome,DIET Dept.,Italy","DIET Dept., Sapienza University of Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,DIET Dept.,Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"DIET Dept., Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.725,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7299672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9976999759674072,"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":0.7863785028457642},{"id":"https://openalex.org/keywords/ambisonics","display_name":"Ambisonics","score":0.7725679874420166},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.6323969960212708},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5547409057617188},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.547698438167572},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5129222869873047},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.49324244260787964},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.48852670192718506},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.4827393889427185},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4821738600730896},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4314875602722168},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3998171389102936},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3788050711154938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3293546438217163},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.28791093826293945},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.13088396191596985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863785028457642},{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.7725679874420166},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.6323969960212708},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5547409057617188},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.547698438167572},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5129222869873047},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49324244260787964},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.48852670192718506},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.4827393889427185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4821738600730896},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4314875602722168},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3998171389102936},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3788050711154938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3293546438217163},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.28791093826293945},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.13088396191596985},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10433925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10433925","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1714441","is_oa":false,"landing_page_url":"https://hdl.handle.net/11573/1714441","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W4225270933","https://openalex.org/W4283076784","https://openalex.org/W6800673378","https://openalex.org/W6839296024"],"related_works":["https://openalex.org/W4387872666","https://openalex.org/W4241811088","https://openalex.org/W2327646860","https://openalex.org/W1977851411","https://openalex.org/W1969257256","https://openalex.org/W4387445755","https://openalex.org/W2289868279","https://openalex.org/W2792033502","https://openalex.org/W4231351862","https://openalex.org/W4212794605"],"abstract_inverted_index":{"The":[0],"primary":[1],"goal":[2],"of":[3,49,64,90,132],"the":[4,60,65,96,130,133,138],"L3DAS23":[5],"Signal":[6],"Processing":[7],"Grand":[8],"Challenge":[9],"at":[10,142],"ICASSP":[11],"2023":[12],"is":[13],"to":[14,123],"promote":[15],"and":[16,36,41,67,100,119],"support":[17,114],"collaborative":[18],"research":[19],"on":[20,32],"machine":[21],"learning":[22],"for":[23,108],"3D":[24,33,37],"audio":[25],"signal":[26],"processing,":[27],"with":[28,71],"a":[29,55,120],"specific":[30],"emphasis":[31],"speech":[34],"enhancement":[35],"Sound":[38],"Event":[39],"Localization":[40],"Detection":[42],"in":[43],"Extended":[44],"Reality":[45],"applications.":[46],"As":[47],"part":[48],"our":[50,125],"latest":[51],"competition,":[52],"we":[53,81,128],"provide":[54],"brand-new":[56],"dataset,":[57],"which":[58],"maintains":[59],"same":[61],"general":[62],"characteristics":[63],"L3DAS21":[66],"L3DAS22":[68],"datasets,":[69],"but":[70],"first-order":[72],"Ambisonics":[73],"recordings":[74],"from":[75],"multiple":[76],"reverberant":[77],"simulated":[78],"environments.":[79],"Moreover,":[80],"start":[82],"exploring":[83],"an":[84],"audio-visual":[85],"scenario":[86],"by":[87,95],"providing":[88],"images":[89],"these":[91],"environments,":[92],"as":[93,117],"perceived":[94],"different":[97],"microphone":[98],"positions":[99],"orientations.":[101],"We":[102],"also":[103],"propose":[104],"updated":[105],"baseline":[106],"models":[107],"both":[109],"tasks":[110],"that":[111],"can":[112],"now":[113],"audio-image":[115],"couples":[116],"input":[118],"supporting":[121],"API":[122],"replicate":[124],"results.":[126],"Finally,":[127],"present":[129],"results":[131],"participants.":[134],"Further":[135],"details":[136],"about":[137],"challenge":[139],"are":[140],"available":[141],"www.l3das.com/icassp2023.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}