{"id":"https://openalex.org/W4392903150","doi":"https://doi.org/10.1109/icassp48485.2024.10448497","title":"Zero- and Few-Shot Sound Event Localization and Detection","display_name":"Zero- and Few-Shot Sound Event Localization and Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903150","doi":"https://doi.org/10.1109/icassp48485.2024.10448497"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5051965288","display_name":"Kazuki Shimada","orcid":"https://orcid.org/0000-0001-5389-2346"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Kazuki Shimada","raw_affiliation_strings":["Sony AI","Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]},{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104321727","display_name":"Kengo Uchida","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kengo Uchida","raw_affiliation_strings":["Sony AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017785136","display_name":"Yuichiro Koyama","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuichiro Koyama","raw_affiliation_strings":["Sony Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084845461","display_name":"Takashi Shibuya","orcid":"https://orcid.org/0000-0002-4277-0164"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takashi Shibuya","raw_affiliation_strings":["Sony AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104117184","display_name":"Shusuke Takahashi","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shusuke Takahashi","raw_affiliation_strings":["Sony Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony AI","Sony Group Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony AI","institution_ids":["https://openalex.org/I2800278093"]},{"raw_affiliation_string":"Sony Group Corporation","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"636","last_page":"640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9940000176429749,"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":0.7371505498886108},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6922022700309753},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5434572696685791},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5269649624824524},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5128827095031738},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5094605088233948},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5004153251647949},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49897313117980957},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.4512641727924347},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4511494040489197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4158972501754761},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38889724016189575}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371505498886108},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6922022700309753},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5434572696685791},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5269649624824524},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5128827095031738},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5094605088233948},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5004153251647949},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49897313117980957},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.4512641727924347},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4511494040489197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4158972501754761},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38889724016189575},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":31,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W2130640900","https://openalex.org/W2570915410","https://openalex.org/W2592109325","https://openalex.org/W2810934215","https://openalex.org/W2962999716","https://openalex.org/W2982680886","https://openalex.org/W2998139081","https://openalex.org/W3015205011","https://openalex.org/W3015622757","https://openalex.org/W3163193264","https://openalex.org/W3163881933","https://openalex.org/W3204441137","https://openalex.org/W3206329344","https://openalex.org/W4205689591","https://openalex.org/W4224919399","https://openalex.org/W4372260310","https://openalex.org/W4372263497","https://openalex.org/W4372266552","https://openalex.org/W4372267873","https://openalex.org/W4375868779","https://openalex.org/W4385822291","https://openalex.org/W6703533685","https://openalex.org/W6749107692","https://openalex.org/W6791353385","https://openalex.org/W6796679619","https://openalex.org/W6801804513","https://openalex.org/W6802517928","https://openalex.org/W6838853441","https://openalex.org/W6853532597","https://openalex.org/W6856096808"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Sound":[0],"event":[1],"localization":[2],"and":[3,10,38,56,96,127,139,159,172],"detection":[4],"(SELD)":[5],"systems":[6,22],"estimate":[7],"direction-of-arrival":[8,131],"(DOA)":[9],"temporal":[11,39],"activation":[12,40],"for":[13],"sets":[14,28],"of":[15,29,41,154,168],"target":[16,30,49],"classes.":[17],"Neural":[18],"network":[19],"(NN)-based":[20],"SELD":[21,58,90,141],"have":[23],"performed":[24,180],"well":[25],"in":[26,60,103,111,192],"various":[27],"classes,":[31],"but":[32],"they":[33],"only":[34],"output":[35,123],"the":[36,108,143,155,165,169],"DOA":[37,98,161],"preset":[42],"classes":[43,50,65],"trained":[44,121,187],"before":[45],"inference.":[46],"To":[47,106],"customize":[48],"after":[51],"training,":[52],"we":[53,62,114],"tackle":[54,107],"zero-":[55,138],"few-shot":[57,140,178],"tasks,":[59,142],"which":[61,119],"set":[63],"new":[64],"with":[66,176,188],"a":[67,71,97,151,160],"text":[68],"sample":[69],"or":[70],"few":[72],"audio":[73,157,174],"samples.":[74],"While":[75],"zero-shot":[76,89],"sound":[77],"classification":[78],"tasks":[79,91],"are":[80],"achievable":[81],"by":[82],"embedding":[83,126],"from":[84],"contrastive":[85],"language-audio":[86],"pretraining":[87],"(CLAP),":[88],"require":[92],"assigning":[93],"an":[94,116,183,193],"activity":[95],"to":[99,122,182],"each":[100],"embedding,":[101],"especially":[102],"overlapping":[104,112],"cases.":[105],"assignment":[109],"problem":[110],"cases,":[113],"propose":[115],"embed-ACCDOA":[117,144,170],"model,":[118],"is":[120],"track-wise":[124],"CLAP":[125,156,173],"corresponding":[128],"activity-coupled":[129],"Cartesian":[130],"(ACCDOA).":[132],"In":[133],"our":[134],"experimental":[135],"evaluations":[136],"on":[137],"model":[145,171],"showed":[146],"better":[147],"location-dependent":[148],"scores":[149],"than":[150],"straightforward":[152],"combination":[153,167],"encoder":[158,175],"estimation":[162],"model.":[163],"Moreover,":[164],"proposed":[166],"zero-or":[177],"samples":[179],"comparably":[181],"official":[184],"baseline":[185],"system":[186],"complete":[189],"train":[190],"data":[191],"evaluation":[194],"dataset.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}