{"id":"https://openalex.org/W3015700860","doi":"https://doi.org/10.1109/icassp40776.2020.9053912","title":"Sound Event Detection by Multitask Learning of Sound Events and Scenes with Soft Scene Labels","display_name":"Sound Event Detection by Multitask Learning of Sound Events and Scenes with Soft Scene Labels","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015700860","doi":"https://doi.org/10.1109/icassp40776.2020.9053912","mag":"3015700860"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5009991655","display_name":"Keisuke Imoto","orcid":"https://orcid.org/0000-0002-0703-8293"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Keisuke Imoto","raw_affiliation_strings":["Ritsumeikan University, Shiga, Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059521640","display_name":"Noriyuki Tonami","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Noriyuki Tonami","raw_affiliation_strings":["Ritsumeikan University, Shiga, Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"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":"Yuma Koizumi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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 Media Intelligence Laboratories, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069311949","display_name":"Ryosuke Yamanishi","orcid":"https://orcid.org/0009-0007-6798-279X"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryosuke Yamanishi","raw_affiliation_strings":["Ritsumeikan University, Shiga, Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103048025","display_name":"Yoichi Yamashita","orcid":"https://orcid.org/0000-0001-5379-9686"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoichi Yamashita","raw_affiliation_strings":["Ritsumeikan University, Shiga, Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5009991655"],"corresponding_institution_ids":["https://openalex.org/I135768898"],"apc_list":null,"apc_paid":null,"fwci":4.6976,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.95786702,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"621","last_page":"625"},"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":0.9973999857902527,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7155832052230835},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6611349582672119},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5921390056610107},{"id":"https://openalex.org/keywords/sound-analysis","display_name":"Sound analysis","score":0.5353622436523438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4956611394882202},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.480726033449173},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.42639249563217163},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.39403975009918213},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3536331057548523},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.21409037709236145},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0864776074886322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7155832052230835},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6611349582672119},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5921390056610107},{"id":"https://openalex.org/C2984030306","wikidata":"https://www.wikidata.org/wiki/Q4819857","display_name":"Sound analysis","level":2,"score":0.5353622436523438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4956611394882202},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.480726033449173},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.42639249563217163},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.39403975009918213},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3536331057548523},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.21409037709236145},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0864776074886322},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1506627523","https://openalex.org/W1533561824","https://openalex.org/W1600745603","https://openalex.org/W1605026219","https://openalex.org/W1821462560","https://openalex.org/W1822987211","https://openalex.org/W2123843894","https://openalex.org/W2134426937","https://openalex.org/W2135342008","https://openalex.org/W2160335114","https://openalex.org/W2160860215","https://openalex.org/W2408239454","https://openalex.org/W2526050071","https://openalex.org/W2527564651","https://openalex.org/W2566935005","https://openalex.org/W2591013610","https://openalex.org/W2746554716","https://openalex.org/W2751116311","https://openalex.org/W2775505379","https://openalex.org/W2897802972","https://openalex.org/W2899595852","https://openalex.org/W2940696344","https://openalex.org/W2972548957","https://openalex.org/W2972581694","https://openalex.org/W2997308807","https://openalex.org/W3121952123","https://openalex.org/W6630111507","https://openalex.org/W6632323398","https://openalex.org/W6636246373","https://openalex.org/W6638523607","https://openalex.org/W6683682394","https://openalex.org/W6743647910","https://openalex.org/W6747331233"],"related_works":["https://openalex.org/W3135110545","https://openalex.org/W648271442","https://openalex.org/W4403326351","https://openalex.org/W344556491","https://openalex.org/W4214853384","https://openalex.org/W2489046492","https://openalex.org/W4395961021","https://openalex.org/W1572151855","https://openalex.org/W1970806855","https://openalex.org/W3111845911"],"abstract_inverted_index":{"Sound":[0,165],"event":[1],"detection":[2],"(SED)":[3],"and":[4,20,37,52,75,89,137,157,168],"acoustic":[5,38,105,119,144],"scene":[6,66],"classification":[7],"(ASC)":[8],"are":[9,22,91,159],"major":[10],"tasks":[11],"in":[12,45,56,94,103,116,185],"environmental":[13],"sound":[14,18,35,50,73,87,99,112,155],"analysis.":[15],"Considering":[16],"that":[17,175],"events":[19,36,51,74,88,100,113,156],"scenes":[21,39,53,90,158],"closely":[23],"related":[24],"to":[25,68,85,149,153],"each":[26],"other,":[27],"some":[28,104,111],"works":[29],"have":[30],"addressed":[31],"joint":[32],"analyses":[33],"of":[34,49,135,143],"based":[40,132],"on":[41,107,133],"multitask":[42],"learning":[43],"(MTL),":[44],"which":[46,86,146,154],"the":[47,70,78,83,95,108,140,151,176,180],"knowledge":[48],"can":[54],"help":[55],"estimating":[57],"them":[58],"mutually.":[59],"The":[60],"conventional":[61,79,189],"MTL-based":[62,190],"methods":[63,80],"utilize":[64],"one-hot":[65],"labels":[67,142],"train":[69],"relationship":[71],"between":[72],"scenes;":[76,106],"thus,":[77],"cannot":[81],"model":[82,150],"extent":[84,152],"related.":[92,160],"However,":[93],"real":[96],"environment,":[97],"common":[98],"may":[101],"occur":[102,114],"other":[109],"hand,":[110],"only":[115],"a":[117,127],"limited":[118],"scene.":[120],"In":[121],"this":[122],"paper,":[123],"we":[124],"thus":[125],"propose":[126],"new":[128],"method":[129,178],"for":[130],"SED":[131,136,181],"MTL":[134],"ASC":[138],"using":[139,163],"soft":[141],"scenes,":[145],"enable":[147],"us":[148],"Experiments":[161],"conducted":[162],"TUT":[164,169],"Events":[166],"2016/2017":[167],"Acoustic":[170],"Scenes":[171],"2016":[172],"datasets":[173],"show":[174],"proposed":[177],"improves":[179],"performance":[182],"by":[183],"3.80%":[184],"F-score":[186],"compared":[187],"with":[188],"SED.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}