{"id":"https://openalex.org/W4408345854","doi":"https://doi.org/10.1109/icassp49660.2025.10890626","title":"Source-Aware Spatial Self-Supervision for Sound Event Localization and Detection","display_name":"Source-Aware Spatial Self-Supervision for Sound Event Localization and Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345854","doi":"https://doi.org/10.1109/icassp49660.2025.10890626"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5051114741","display_name":"Yuji Nozaki","orcid":"https://orcid.org/0000-0002-4193-5588"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuto Nozaki","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031341888","display_name":"Masaki Onishi","orcid":"https://orcid.org/0000-0002-4580-4868"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaki Onishi","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology,Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051114741"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":1.5743,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78231496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9937000274658203,"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/T10860","display_name":"Speech and Audio Processing","score":0.9894000291824341,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6883634924888611},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5931829214096069},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4627615809440613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34258487820625305},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18977594375610352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6883634924888611},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5931829214096069},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4627615809440613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34258487820625305},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18977594375610352},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W1845880232","https://openalex.org/W2072548008","https://openalex.org/W2113990625","https://openalex.org/W2563666542","https://openalex.org/W2759976799","https://openalex.org/W2810934215","https://openalex.org/W2924334974","https://openalex.org/W2936774411","https://openalex.org/W2937284863","https://openalex.org/W2982680886","https://openalex.org/W2998139081","https://openalex.org/W3015678657","https://openalex.org/W3016037102","https://openalex.org/W3081267827","https://openalex.org/W3163193264","https://openalex.org/W3163257865","https://openalex.org/W3163881933","https://openalex.org/W3198425604","https://openalex.org/W3206329344","https://openalex.org/W3206996142","https://openalex.org/W4205689591","https://openalex.org/W4362653188","https://openalex.org/W4385823069","https://openalex.org/W4388117343","https://openalex.org/W4392903150","https://openalex.org/W4392903751","https://openalex.org/W4402112272","https://openalex.org/W4404914582","https://openalex.org/W6631190155","https://openalex.org/W6779923105","https://openalex.org/W6784117923","https://openalex.org/W6838853441","https://openalex.org/W6853532597","https://openalex.org/W6862631807"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2909726438"],"abstract_inverted_index":{"This":[0,94],"paper":[1],"presents":[2],"a":[3,85,90,121,140,144,165],"source-aware":[4],"spatial":[5,56,99],"self-supervised":[6,74],"learning":[7],"(SSL)":[8],"method":[9,134,158],"for":[10,107],"sound":[11,32,81,130],"event":[12],"localization":[13],"and":[14,34,61,66,78],"detection":[15],"(SELD)":[16],"based":[17],"on":[18,55],"neural":[19,46,91,97],"blind":[20],"source":[21],"separation":[22],"(BSS).":[23],"SELD":[24,141,161],"involves":[25],"estimating":[26],"both":[27],"the":[28,114,152],"temporal":[29],"activations":[30],"of":[31,37,89,128,147,168],"classes":[33],"their":[35,53],"directions":[36],"arrival":[38],"(DOAs)":[39],"from":[40],"multichannel":[41,104],"audio":[42],"signals.":[43],"While":[44],"deep":[45],"networks":[47],"have":[48],"been":[49],"successful":[50],"in":[51,120],"SELD,":[52],"reliance":[54],"supervision,":[57],"including":[58],"class":[59],"labels":[60],"DOAs,":[62],"makes":[63],"annotation":[64],"challenging":[65],"time-intensive.":[67],"To":[68],"address":[69],"this":[70],"limitation,":[71],"we":[72],"propose":[73],"pre-training":[75],"to":[76,116,125,138],"separate":[77],"localize":[79],"moving":[80],"sources":[82,119],"by":[83],"maximizing":[84],"log-marginal":[86],"posterior":[87],"probability":[88],"BSS":[92],"model.":[93],"model,":[95],"called":[96],"full-rank":[98],"covariance":[100],"analysis,":[101],"requires":[102],"only":[103],"mixture":[105],"signals":[106],"training.":[108],"Our":[109],"BSS-based":[110],"framework":[111],"explicitly":[112],"trains":[113],"model":[115,142],"distinguish":[117],"multiple":[118,129],"mixture,":[122],"enabling":[123],"it":[124],"predict":[126],"DOAs":[127],"events.":[131],"The":[132,149],"proposed":[133],"thus":[135],"enables":[136],"us":[137],"train":[139],"with":[143,151,164],"small":[145],"amount":[146,167],"annotation.":[148],"experiments":[150],"STARSS23":[153],"dataset":[154],"show":[155],"that":[156],"our":[157],"outperforms":[159],"baseline":[160],"models":[162],"trained":[163],"limited":[166],"supervised":[169],"data.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}