{"id":"https://openalex.org/W3160333138","doi":"https://doi.org/10.1109/icassp39728.2021.9414949","title":"Impact of Sound Duration and Inactive Frames on Sound Event Detection Performance","display_name":"Impact of Sound Duration and Inactive Frames on Sound Event Detection Performance","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160333138","doi":"https://doi.org/10.1109/icassp39728.2021.9414949","mag":"3160333138"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/I133984924","display_name":"Doshisha University","ror":"https://ror.org/01fxdkm29","country_code":"JP","type":"education","lineage":["https://openalex.org/I133984924"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Imoto","raw_affiliation_strings":["Doshisha University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Doshisha University","institution_ids":["https://openalex.org/I133984924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003163052","display_name":"Sakiko Mishima","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sakiko Mishima","raw_affiliation_strings":["NEC Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051445503","display_name":"Yumi Arai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yumi Arai","raw_affiliation_strings":["NEC Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041279908","display_name":"Reishi Kondo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reishi Kondo","raw_affiliation_strings":["NEC Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7956,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85224586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"860","last_page":"864"},"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":0.9995999932289124,"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":0.9962000250816345,"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/sound","display_name":"Sound (geography)","score":0.74588942527771},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6880438327789307},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.6691594123840332},{"id":"https://openalex.org/keywords/sound-exposure","display_name":"Sound exposure","score":0.5597241520881653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.531599760055542},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.47882726788520813},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.46439462900161743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3508908748626709},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14056983590126038},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0984724760055542}],"concepts":[{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.74588942527771},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6880438327789307},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.6691594123840332},{"id":"https://openalex.org/C2776532659","wikidata":"https://www.wikidata.org/wiki/Q2230528","display_name":"Sound exposure","level":3,"score":0.5597241520881653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.531599760055542},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.47882726788520813},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.46439462900161743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3508908748626709},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14056983590126038},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0984724760055542},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/10","score":0.41999998688697815,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1696349731","display_name":"Sound event detection method capable of analyzing any environmental sound","funder_award_id":"19K20304","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1600745603","https://openalex.org/W2160335114","https://openalex.org/W2398030828","https://openalex.org/W2526050071","https://openalex.org/W2552032035","https://openalex.org/W2566935005","https://openalex.org/W2591013610","https://openalex.org/W2746554716","https://openalex.org/W2759976799","https://openalex.org/W2775505379","https://openalex.org/W2801393360","https://openalex.org/W2884011836","https://openalex.org/W2903432333","https://openalex.org/W2963351448","https://openalex.org/W2964098128","https://openalex.org/W2968917279","https://openalex.org/W2973152780","https://openalex.org/W2994689640","https://openalex.org/W2997892289","https://openalex.org/W3012980069","https://openalex.org/W3015205011","https://openalex.org/W3016059657","https://openalex.org/W3016195076","https://openalex.org/W3034328552","https://openalex.org/W3049446265","https://openalex.org/W4289329167","https://openalex.org/W6747331233","https://openalex.org/W6753516609","https://openalex.org/W6757052456","https://openalex.org/W6767164110"],"related_works":["https://openalex.org/W2348837382","https://openalex.org/W746329893","https://openalex.org/W4205872570","https://openalex.org/W300569899","https://openalex.org/W1983176070","https://openalex.org/W2622283787","https://openalex.org/W255711939","https://openalex.org/W2136869966","https://openalex.org/W1916586857","https://openalex.org/W2079851506"],"abstract_inverted_index":{"In":[0,102],"many":[1,79],"methods":[2],"of":[3,23,84,109],"sound":[4,24,30,35,44,57,70,85,110],"event":[5,31,36,45,58],"detection":[6],"(SED),":[7],"a":[8,39,62,93],"segmented":[9],"time":[10,82],"frame":[11],"is":[12,48],"regarded":[13],"as":[14,124],"one":[15],"data":[16,64,95],"sample":[17],"to":[18,73],"model":[19],"training.":[20],"The":[21],"durations":[22],"events":[25,71,86],"greatly":[26],"depend":[27],"on":[28,115],"the":[29,34,43,51,54,107],"class,":[32],"e.g.,":[33],"\"fan\"":[37],"has":[38],"long":[40],"duration,":[41],"whereas":[42],"\"mouse":[46],"clicking\"":[47],"instantaneous.":[49],"Thus,":[50],"difference":[52],"in":[53,61,66],"duration":[55,111],"between":[56,97],"classes":[59],"results":[60],"serious":[63],"imbalance":[65,96,148],"SED.":[67],"Moreover,":[68],"most":[69],"tend":[72],"occur":[74],"occasionally;":[75],"therefore,":[76],"there":[77],"are":[78],"more":[80],"inactive":[81,100,113],"frames":[83,114],"than":[87],"active":[88,98],"frames.":[89,101],"This":[90],"also":[91],"causes":[92],"severe":[94],"and":[99,112,134],"this":[103,147],"paper,":[104],"we":[105,140,145],"investigate":[106],"impact":[108],"SED":[116],"performance":[117],"by":[118],"introducing":[119],"four":[120],"loss":[121],"functions,":[122],"such":[123],"simple":[125],"reweighting":[126],"loss,":[127,130,133],"inverse":[128],"frequency":[129],"asymmetric":[131],"focal":[132,135],"batch":[136],"Tversky":[137],"loss.":[138],"Then,":[139],"provide":[141],"insights":[142],"into":[143],"how":[144],"tackle":[146],"problem.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2025-10-10T00:00:00"}
