{"id":"https://openalex.org/W4375868779","doi":"https://doi.org/10.1109/icassp49357.2023.10096460","title":"AD-YOLO: You Look Only Once in Training Multiple Sound Event Localization and Detection","display_name":"AD-YOLO: You Look Only Once in Training Multiple Sound Event Localization and Detection","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868779","doi":"https://doi.org/10.1109/icassp49357.2023.10096460"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5054938286","display_name":"Jin Sob Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jin Sob Kim","raw_affiliation_strings":["Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103110752","display_name":"Hyun Joon Park","orcid":"https://orcid.org/0000-0002-5308-6675"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun Joon Park","raw_affiliation_strings":["Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001866594","display_name":"Woo-Seok Shin","orcid":"https://orcid.org/0000-0002-8475-4795"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wooseok Shin","raw_affiliation_strings":["Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024995454","display_name":"Sung Won Han","orcid":"https://orcid.org/0000-0002-0040-3542"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung Won Han","raw_affiliation_strings":["Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,School of Industrial and Management Engineering,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I197347611"]},{"raw_affiliation_string":"School of Industrial and Management Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054938286"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":3.2604,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93014085,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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":0.9998999834060669,"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/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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.967199981212616,"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/robustness","display_name":"Robustness (evolution)","score":0.7333900928497314},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7082277536392212},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6784047484397888},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5398944616317749},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47774070501327515},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4297504723072052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40216580033302307},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09797677397727966}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7333900928497314},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7082277536392212},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6784047484397888},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5398944616317749},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47774070501327515},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4297504723072052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40216580033302307},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09797677397727966},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321373","display_name":"Korea University","ror":"https://ror.org/047dqcg40"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1673310716","https://openalex.org/W1844944916","https://openalex.org/W2135131618","https://openalex.org/W2292996718","https://openalex.org/W2752782242","https://openalex.org/W2810934215","https://openalex.org/W2883787264","https://openalex.org/W2936774411","https://openalex.org/W2942551338","https://openalex.org/W2950635152","https://openalex.org/W2963037989","https://openalex.org/W2982680886","https://openalex.org/W2998139081","https://openalex.org/W3083274258","https://openalex.org/W3098454764","https://openalex.org/W3117314925","https://openalex.org/W3163193264","https://openalex.org/W3163881933","https://openalex.org/W3206329344","https://openalex.org/W4221146826","https://openalex.org/W4282031641","https://openalex.org/W4287120192","https://openalex.org/W4287766186","https://openalex.org/W6637131181"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200","https://openalex.org/W2390487542"],"abstract_inverted_index":{"Sound":[0],"event":[1],"localization":[2],"and":[3,130],"detection":[4],"(SELD)":[5],"combines":[6],"the":[7,13,47,61,73,88,91,95,100],"identification":[8],"of":[9,16,60,99,102],"sound":[10,77,103],"events":[11],"with":[12],"corresponding":[14],"directions":[15],"arrival":[17],"(DOA).":[18],"Recently,":[19],"event-oriented":[20],"track":[21],"output":[22],"formats":[23],"have":[24,34],"been":[25],"adopted":[26],"to":[27,75,84,93],"solve":[28],"this":[29],"problem;":[30],"however,":[31],"they":[32],"still":[33],"limited":[35],"generalization":[36],"toward":[37],"real-world":[38],"problems":[39],"in":[40,134],"an":[41,51,58],"unknown":[42],"polyphony":[43,96,136],"environment.":[44],"To":[45],"address":[46],"issue,":[48],"we":[49],"proposed":[50],"angular-distance-based":[52],"multiple":[53],"SELD":[54,117],"(AD-YOLO),":[55],"which":[56],"is":[57],"adaptation":[59],"\"You":[62],"Look":[63],"Only":[64],"Once\"":[65],"algorithm":[66],"for":[67],"SELD.":[68],"The":[69,120],"AD-YOLO":[70,107,125],"format":[71,89],"allows":[72],"model":[74,92],"learn":[76],"occurrences":[78],"location-sensitively":[79],"by":[80],"assigning":[81],"class":[82],"responsibility":[83],"DOA":[85],"predictions.":[86],"Hence,":[87],"enables":[90],"handle":[94],"problem,":[97],"regardless":[98],"number":[101],"overlaps.":[104],"We":[105],"evaluated":[106],"on":[108],"DCASE":[109],"2020-2022":[110],"challenge":[111],"Task":[112],"3":[113],"datasets":[114],"using":[115],"four":[116],"objective":[118],"metrics.":[119],"experimental":[121],"results":[122],"show":[123],"that":[124],"achieved":[126],"outstanding":[127],"performance":[128],"overall":[129],"also":[131],"accomplished":[132],"robustness":[133],"class-homogeneous":[135],"environments.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}