{"id":"https://openalex.org/W7081996574","doi":"https://doi.org/10.1109/access.2025.3609479","title":"Spatial Annotation-Free Sound Event Localization and Detection via Spatial Instance Classification","display_name":"Spatial Annotation-Free Sound Event Localization and Detection via Spatial Instance Classification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7081996574","doi":"https://doi.org/10.1109/access.2025.3609479"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3609479","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3609479","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3609479","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Masahiro Yasuda","orcid":"https://orcid.org/0000-0003-2776-9701"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Yasuda","raw_affiliation_strings":["NTT, Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2776-9701","affiliations":[{"raw_affiliation_string":"NTT, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Noboru Harada","orcid":"https://orcid.org/0000-0002-1759-4533"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noboru Harada","raw_affiliation_strings":["NTT, Inc., Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1759-4533","affiliations":[{"raw_affiliation_string":"NTT, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shoichiro Saito","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I2801547476","display_name":"NTT Medical Center","ror":"https://ror.org/0285prp25","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I2801547476"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoichiro Saito","raw_affiliation_strings":["NTT, Inc., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT, Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I2801547476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056281759","display_name":"Nobutaka Ono","orcid":"https://orcid.org/0000-0003-4242-2773"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ono","raw_affiliation_strings":["Tokyo Metropolitan University, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4242-2773","affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.59191815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"171613","last_page":"171625"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6442999839782715,"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"}},"topics":[{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6442999839782715,"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"}},{"id":"https://openalex.org/T13067","display_name":"Geological Modeling and Analysis","score":0.02539999969303608,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14311","display_name":"Electrical and Electromagnetic Research","score":0.02160000056028366,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5515999794006348},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4553000032901764},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4447000026702881},{"id":"https://openalex.org/keywords/spatial-relation","display_name":"Spatial relation","score":0.42879998683929443},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.4092999994754791},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.3968999981880188},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.3504999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267000079154968},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5515999794006348},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4553000032901764},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4375999867916107},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.3968999981880188},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3546000123023987},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C68236139","wikidata":"https://www.wikidata.org/wiki/Q765652","display_name":"Sound localization","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C17825722","wikidata":"https://www.wikidata.org/wiki/Q17285","display_name":"Plane (geometry)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C196070930","wikidata":"https://www.wikidata.org/wiki/Q598190","display_name":"Correlogram","level":2,"score":0.2685000002384186}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3609479","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3609479","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:125a5ab6af1a4f799ea1dfc90f976c1f","is_oa":true,"landing_page_url":"https://doaj.org/article/125a5ab6af1a4f799ea1dfc90f976c1f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 171613-171625 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3609479","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3609479","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1981446207","https://openalex.org/W2046317813","https://openalex.org/W2055131649","https://openalex.org/W2113638573","https://openalex.org/W2204091679","https://openalex.org/W2560886373","https://openalex.org/W2618657287","https://openalex.org/W2763188033","https://openalex.org/W2778725237","https://openalex.org/W2883787264","https://openalex.org/W2912056372","https://openalex.org/W2962865004","https://openalex.org/W2982429715","https://openalex.org/W2982680886","https://openalex.org/W3016037102","https://openalex.org/W3083274258","https://openalex.org/W3163193264","https://openalex.org/W3203177955","https://openalex.org/W3206329344","https://openalex.org/W3213455868","https://openalex.org/W4205689591","https://openalex.org/W4221167652","https://openalex.org/W4324116353","https://openalex.org/W4372346897","https://openalex.org/W4375869216","https://openalex.org/W4388820630","https://openalex.org/W4392903150","https://openalex.org/W4392903899","https://openalex.org/W4392904420","https://openalex.org/W4393241094","https://openalex.org/W4401991047","https://openalex.org/W4404914582","https://openalex.org/W4405114436","https://openalex.org/W4408353923"],"related_works":[],"abstract_inverted_index":{"Sound":[0],"Event":[1],"Localization":[2],"and":[3,16,123,164],"Detection":[4],"(SELD)":[5],"typically":[6],"relies":[7],"on":[8,118,178],"strongly":[9],"labeled":[10],"data":[11],"that":[12,33,95],"specify":[13],"when,":[14],"where,":[15],"which":[17],"sounds":[18],"occur,":[19],"resulting":[20],"in":[21,136],"high":[22],"annotation":[23],"costs.":[24],"To":[25],"address":[26],"this":[27],"challenge,":[28],"we":[29,109],"present":[30],"a":[31,54,57,86,119,168,179],"framework":[32],"enables":[34],"SELD":[35,101,159,172,192,212],"training":[36],"without":[37,199],"spatial":[38,41,61,87,111,200],"labels,":[39],"termed":[40],"annotation-free":[42,112],"SELD.":[43,113],"The":[44,202],"core":[45],"idea":[46],"is":[47,83,125],"to":[48,127,158,167],"reinterpret":[49],"source":[50],"localization\u2014traditionally":[51],"handled":[52],"as":[53,85,131,133,143],"regression":[55],"problem\u2014as":[56],"classification":[58,63],"task":[59],"called":[60],"instance":[62],"(SIC).":[64],"SIC":[65,105,114,151,189],"first":[66],"partitions":[67],"the":[68,76,93,134,148,207],"observation":[69],"region":[70,139],"into":[71],"sub-regions.":[72],"For":[73],"each":[74,137],"sub-region,":[75],"acoustic":[77],"signal":[78],"capturing":[79],"its":[80],"sound":[81,97,135,197],"events":[82,175,198],"extracted":[84,142],"instance.":[88,145],"Classifying":[89],"these":[90],"instances":[91],"reveals":[92],"sub-regions":[94],"contain":[96],"events,":[98],"thereby":[99],"providing":[100],"functionality.":[102],"By":[103],"solving":[104],"under":[106],"weak":[107],"supervision,":[108],"realize":[110],"does":[115],"not":[116],"depend":[117],"specific":[120],"microphone":[121,215],"configuration,":[122],"it":[124],"expected":[126],"be":[128,141],"generally":[129],"applicable":[130],"long":[132],"divided":[138],"can":[140],"an":[144],"We":[146],"validate":[147],"generality":[149],"of":[150,195,209],"through":[152],"two":[153],"contrasting":[154],"experiments:":[155],"(i)":[156],"application":[157,166],"using":[160,182],"first-order":[161],"Ambisonics":[162],"(FOA),":[163],"(ii)":[165],"newly":[169],"introduced":[170],"distributed":[171],"task,":[173],"where":[174],"are":[176],"localized":[177],"2D":[180],"plane":[181],"widely":[183],"spaced":[184],"microphones.":[185],"In":[186],"both":[187],"settings,":[188],"effectively":[190],"trains":[191],"systems":[193],"capable":[194],"localizing":[196],"annotations.":[201],"proposed":[203],"approach,":[204],"therefore,":[205],"facilitates":[206],"development":[208],"practical,":[210],"spatial-annotation-free":[211],"across":[213],"diverse":[214],"setups.":[216]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
