{"id":"https://openalex.org/W4408353923","doi":"https://doi.org/10.1109/icassp49660.2025.10889696","title":"Spatial Annotation-free Training for Sound Event Localization and Detection","display_name":"Spatial Annotation-free Training for Sound Event Localization and Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353923","doi":"https://doi.org/10.1109/icassp49660.2025.10889696"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889696","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":"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/A5017806490","display_name":"Masahiro Yasuda","orcid":"https://orcid.org/0000-0002-8384-8167"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Yasuda","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108799515","display_name":"Shoichiro Saito","orcid":"https://orcid.org/0000-0002-8712-0464"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoichiro Saito","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079219086","display_name":"Nao Sato","orcid":"https://orcid.org/0000-0002-2728-888X"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nao Sato","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054467679","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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noboru Harada","raw_affiliation_strings":["NTT Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":3.0156,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88556172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"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":0.9997000098228455,"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9921000003814697,"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":0.984499990940094,"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":0.7406263947486877},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6628092527389526},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6233004927635193},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5900245904922485},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5507319569587708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.509840190410614},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.41002941131591797},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34912392497062683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3416389226913452},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.338096559047699},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10474199056625366},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0828414261341095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7406263947486877},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6628092527389526},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6233004927635193},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5900245904922485},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5507319569587708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.509840190410614},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.41002941131591797},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34912392497062683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3416389226913452},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.338096559047699},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10474199056625366},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0828414261341095},{"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},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889696","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":26,"referenced_works":["https://openalex.org/W2046317813","https://openalex.org/W2113638573","https://openalex.org/W2204091679","https://openalex.org/W2560886373","https://openalex.org/W2810934215","https://openalex.org/W2883787264","https://openalex.org/W2912599552","https://openalex.org/W2962865004","https://openalex.org/W2982429715","https://openalex.org/W2982680886","https://openalex.org/W3016037102","https://openalex.org/W3206329344","https://openalex.org/W4221167652","https://openalex.org/W4375869216","https://openalex.org/W4378373648","https://openalex.org/W4388820630","https://openalex.org/W4392903150","https://openalex.org/W4392903899","https://openalex.org/W4392904420","https://openalex.org/W4393241094","https://openalex.org/W4404914582","https://openalex.org/W6743647910","https://openalex.org/W6796679619","https://openalex.org/W6797253786","https://openalex.org/W6838853441","https://openalex.org/W6853532597"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W4405124681","https://openalex.org/W1533177136","https://openalex.org/W4380994516"],"abstract_inverted_index":{"Sound":[0],"Event":[1],"Localization":[2],"and":[3,14,42,71,99],"Detection":[4],"(SELD)":[5],"is":[6,77,173],"the":[7,11,72,127,166,170,184,187],"task":[8],"of":[9,16,19,62,74,169,186],"estimating":[10],"class,":[12],"duration,":[13],"direction":[15],"arrival":[17],"(DOA)":[18],"sound":[20,44,97,128],"events.":[21],"State-of-the-art":[22],"SELD":[23,93],"systems":[24,47],"use":[25],"a":[26,92,103,157],"data-driven":[27],"approach":[28],"based":[29],"on":[30,52],"Deep":[31],"Neural":[32],"Networks":[33],"(DNNs)":[34],"to":[35,49,55],"deal":[36],"with":[37],"complex":[38],"situations":[39],"involving":[40],"overlapping":[41],"moving":[43],"sources.":[45],"Such":[46],"need":[48],"be":[50],"trained":[51,135],"real-recording":[53],"data":[54,76,172,176,181],"succeed":[56],"in":[57,131],"real-world":[58,63],"situations.":[59],"However,":[60],"annotation":[61],"data,":[64],"especially":[65],"spatial":[66,85,147,162],"annotation,":[67],"incurs":[68],"huge":[69],"costs,":[70],"amount":[73,168],"labeled":[75],"currently":[78],"insufficiently":[79],"small.":[80],"Therefore,":[81],"we":[82,109],"are":[83,134],"introducing":[84],"annotation-free":[86,180],"training":[87],"for":[88,121],"SELD,":[89],"which":[90],"trains":[91],"system":[94],"using":[95,140],"only":[96],"class":[98],"duration":[100],"labels.":[101],"As":[102],"first":[104,117],"attempt":[105],"at":[106],"this":[107],"task,":[108],"propose":[110],"Beam-based":[111],"Multiple":[112],"Instance":[113],"Learning":[114],"(Beam-MIL).":[115],"Beam-MIL":[116,153],"instantiates":[118],"acoustic":[119],"signals":[120],"each":[122,132,141],"DOA":[123,159],"by":[124,137,178],"beamforming.":[125],"Then,":[126],"events":[129],"contained":[130],"instance":[133],"indirectly":[136],"MIL":[138],"without":[139,161],"instance\u2019s":[142],"ground":[143],"truth":[144],"information,":[145],"i.e.,":[146],"annotation.":[148],"Experimental":[149],"results":[150],"show":[151],"that":[152],"can":[154],"effectively":[155],"train":[156],"valid":[158],"estimator":[160],"annotations.":[163],"Moreover,":[164],"when":[165],"small":[167],"annotated":[171],"available,":[174],"enlarging":[175],"size":[177],"adding":[179],"significantly":[182],"improved":[183],"performance":[185],"system.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}