{"id":"https://openalex.org/W3206329344","doi":"https://doi.org/10.1109/icassp43922.2022.9746384","title":"Multi-ACCDOA: Localizing And Detecting Overlapping Sounds From The Same Class With Auxiliary Duplicating Permutation Invariant Training","display_name":"Multi-ACCDOA: Localizing And Detecting Overlapping Sounds From The Same Class With Auxiliary Duplicating Permutation Invariant Training","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3206329344","doi":"https://doi.org/10.1109/icassp43922.2022.9746384","mag":"3206329344"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746384","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuki Shimada","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017785136","display_name":"Yuichiro Koyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuichiro Koyama","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104117184","display_name":"Shusuke Takahashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shusuke Takahashi","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101589290","display_name":"Naoya Takahashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoya Takahashi","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088754502","display_name":"Yuki Mitsufuji","orcid":"https://orcid.org/0000-0002-6806-6140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.7821,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.98830972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"316","last_page":"320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7045366764068604},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.663822591304779},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6549923419952393},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5856055021286011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5242986083030701},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4789600670337677},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3530105650424957},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33594733476638794},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17276951670646667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7045366764068604},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.663822591304779},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6549923419952393},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5856055021286011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5242986083030701},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4789600670337677},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3530105650424957},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33594733476638794},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17276951670646667},{"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746384","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W2130640900","https://openalex.org/W2135131618","https://openalex.org/W2570915410","https://openalex.org/W2592109325","https://openalex.org/W2622263826","https://openalex.org/W2734774145","https://openalex.org/W2810934215","https://openalex.org/W2889373351","https://openalex.org/W2892163332","https://openalex.org/W2936774411","https://openalex.org/W2942551338","https://openalex.org/W2963173418","https://openalex.org/W2963543871","https://openalex.org/W2982680886","https://openalex.org/W2998139081","https://openalex.org/W3005741390","https://openalex.org/W3013934216","https://openalex.org/W3033731578","https://openalex.org/W3083274258","https://openalex.org/W3096730413","https://openalex.org/W3098454764","https://openalex.org/W3120252178","https://openalex.org/W3163193264","https://openalex.org/W3163881933","https://openalex.org/W3167721750","https://openalex.org/W3171659463","https://openalex.org/W3176079376","https://openalex.org/W3177143793","https://openalex.org/W3204441137","https://openalex.org/W4287120192","https://openalex.org/W4287766186","https://openalex.org/W6739622702","https://openalex.org/W6749107692","https://openalex.org/W6753285601","https://openalex.org/W6773738941","https://openalex.org/W6775848399","https://openalex.org/W6779923105","https://openalex.org/W6782346483","https://openalex.org/W6788349323","https://openalex.org/W6796058780","https://openalex.org/W6796679619","https://openalex.org/W6797253786","https://openalex.org/W6797669297","https://openalex.org/W6801804513"],"related_works":["https://openalex.org/W2594778474","https://openalex.org/W2944183083","https://openalex.org/W3104453097","https://openalex.org/W2949607517","https://openalex.org/W2951830772","https://openalex.org/W4301731691","https://openalex.org/W4285790638","https://openalex.org/W1971215949","https://openalex.org/W2951242027","https://openalex.org/W1769744536"],"abstract_inverted_index":{"Sound":[0],"event":[1,13,31,72],"localization":[2],"and":[3,11,33,96,109,163],"detection":[4],"(SELD)":[5],"involves":[6],"identifying":[7],"the":[8,12,24,70,83,86,114,118,123,134,140,144,150,156,160,165,172,180,184],"direction-of-arrival":[9],"(DOA)":[10],"class.":[14,125],"The":[15,36,104,126],"SELD":[16,52,191],"methods":[17,38,192],"with":[18,54,120,139,149,159,164,193],"a":[19,51,55,59,66,93],"class-wise":[20,37,87,127,166],"output":[21,40,111],"format":[22,106,136,162],"make":[23],"model":[25,115,157],"predict":[26],"activities":[27],"of":[28,85,133],"all":[29],"sound":[30],"classes":[32],"corresponding":[34],"locations.":[35,76],"can":[39],"activity-coupled":[41],"Cartesian":[42],"DOA":[43],"(ACCDOA)":[44],"vectors,":[45],"which":[46],"enable":[47],"us":[48],"to":[49,92,116,137,189],"solve":[50,117],"task":[53],"single":[56,60],"target":[57,142],"using":[58],"network.":[61],"However,":[62],"there":[63],"is":[64],"still":[65],"challenge":[67],"in":[68,179],"detecting":[69],"same":[71,124,141,173],"class":[73,174],"from":[74,122,171],"multiple":[75],"To":[77],"overcome":[78],"this":[79],"problem":[80],"while":[81,175],"maintaining":[82,176],"advantages":[84],"format,":[88],"we":[89],"extended":[90],"ACCDOA":[91],"multi":[94],"one":[95],"proposed":[97,185],"auxiliary":[98],"duplicating":[99],"permutation":[100],"invariant":[101],"training":[102],"(ADPIT).":[103],"multi-ACCDOA":[105,135,161],"(a":[107],"class-":[108],"track-wise":[110],"format)":[112],"enables":[113,130],"cases":[119],"overlaps":[121],"ADPIT":[128,167],"scheme":[129],"each":[131],"track":[132],"learn":[138],"as":[143],"single-ACCDOA":[145],"format.":[146],"In":[147],"evaluations":[148],"DCASE":[151],"2021":[152],"Task":[153],"3":[154],"dataset,":[155],"trained":[158],"detects":[168],"overlapping":[169],"events":[170],"its":[177],"performance":[178],"other":[181],"cases.":[182],"Also,":[183],"method":[186],"performed":[187],"comparably":[188],"state-of-the-art":[190],"fewer":[194],"parameters.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
