{"id":"https://openalex.org/W3015420744","doi":"https://doi.org/10.1109/icassp40776.2020.9053702","title":"Scene-Dependent Acoustic Event Detection with Scene Conditioning and Fake-Scene-Conditioned Loss","display_name":"Scene-Dependent Acoustic Event Detection with Scene Conditioning and Fake-Scene-Conditioned Loss","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015420744","doi":"https://doi.org/10.1109/icassp40776.2020.9053702","mag":"3015420744"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053702","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":"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/A5113730169","display_name":"Tatsuya Komatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Komatsu","raw_affiliation_strings":["LINE Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","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":false,"raw_author_name":"Keisuke Imoto","raw_affiliation_strings":["Ritsumeikan University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021883714","display_name":"Masahito Togami","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahito Togami","raw_affiliation_strings":["LINE Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation, Japan","institution_ids":["https://openalex.org/I4210096607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8216,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.70375396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"646","last_page":"650"},"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":0.9984999895095825,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9833999872207642,"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":0.7042983770370483},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7037256360054016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6538257598876953},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6042992472648621},{"id":"https://openalex.org/keywords/conditioning","display_name":"Conditioning","score":0.5257666707038879},{"id":"https://openalex.org/keywords/scene-statistics","display_name":"Scene statistics","score":0.5029427409172058},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4765127897262573},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1550152599811554},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1195492148399353},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.11513382196426392}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7042983770370483},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7037256360054016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6538257598876953},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6042992472648621},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.5257666707038879},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.5029427409172058},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4765127897262573},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1550152599811554},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1195492148399353},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.11513382196426392},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053702","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053702","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2009504845","https://openalex.org/W2090200552","https://openalex.org/W2095147901","https://openalex.org/W2118230268","https://openalex.org/W2135342008","https://openalex.org/W2146078527","https://openalex.org/W2341412280","https://openalex.org/W2398030828","https://openalex.org/W2527564651","https://openalex.org/W2591013610","https://openalex.org/W2746554716","https://openalex.org/W2886877375","https://openalex.org/W2897435617","https://openalex.org/W2963099423","https://openalex.org/W2964121744","https://openalex.org/W2972581694","https://openalex.org/W2997308807","https://openalex.org/W4289465850","https://openalex.org/W6631190155","https://openalex.org/W6753847621","https://openalex.org/W6756022612","https://openalex.org/W6941349294"],"related_works":["https://openalex.org/W2344176346","https://openalex.org/W2052307325","https://openalex.org/W1489675464","https://openalex.org/W1881653995","https://openalex.org/W2365635896","https://openalex.org/W2062287200","https://openalex.org/W2004526709","https://openalex.org/W2063101141","https://openalex.org/W2108281685","https://openalex.org/W2032527201"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"scene-dependent":[5],"acoustic":[6,31],"event":[7,140,156,199],"detection":[8],"(AED)":[9],"with":[10,90,126,146,174],"scene":[11,32,47],"conditioning":[12,48],"and":[13,57,97,110,185],"fake-scene-conditioned":[14,74,101,107,147],"loss.":[15,82],"The":[16,35,100],"proposed":[17,63,150,167],"method":[18,64,151,168],"employs":[19],"a":[20,66,144,160,186],"multitask":[21],"network,":[22],"that":[23,114,138,154,165],"has":[24],"not":[25,116],"only":[26,136],"AED":[27,50,68,81,86,108,134,171],"part":[28,87],"but":[29],"also":[30],"classification":[33],"(ASC).":[34],"scenes":[36,56,92,121,196],"predicted":[37,96],"by":[38],"ASC":[39],"are":[40,122],"employed":[41],"as":[42,93,95],"an":[43,139,155,177],"additional":[44],"feature":[45],"for":[46,195],"of":[49,112,128,183,193],"to":[51,78],"learn":[52,153],"the":[53,62,73,79,85,106,119,132,149,166,170,175,180,189],"relationship":[54],"between":[55,105],"events.":[58],"For":[59],"efficient":[60],"training,":[61,84],"incorporates":[65],"new":[67],"loss":[69,102],"function,":[70],"which":[71],"is":[72,88,103,141,157],"loss,":[75,135,148],"in":[76,118,143,159,179,188],"addition":[77],"conventional":[80,133],"Upon":[83],"conditioned":[89],"fake":[91,120],"well":[94],"true":[98,129],"scenes.":[99],"calculated":[104],"results":[109,163],"labels":[111],"events":[113],"do":[115],"exist":[117],"removed.":[123],"Whereas":[124],"training":[125],"combinations":[127],"scenes/events,":[130],"i.e.,":[131],"reveals":[137],"present":[142],"scene,":[145],"can":[152],"absent":[158],"scene.":[161],"Experimental":[162],"show":[164],"improves":[169],"performance":[172],"compared":[173],"baseline;":[176],"increase":[178],"f1":[181],"score":[182],"23%":[184],"decrease":[187],"false":[190],"alarm":[191],"rate":[192],"56%":[194],"where":[197],"no":[198],"exists.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}