{"id":"https://openalex.org/W4416799582","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249388","title":"Effectiveness of Streaming ASR for Real-Time Laughter and Screaming Detection","display_name":"Effectiveness of Streaming ASR for Real-Time Laughter and Screaming Detection","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799582","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249388"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5120437531","display_name":"Mizuki Kurasawa","orcid":null},"institutions":[{"id":"https://openalex.org/I8488066","display_name":"Chiba Institute of Technology","ror":"https://ror.org/00qwnam72","country_code":"JP","type":"education","lineage":["https://openalex.org/I8488066"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mizuki Kurasawa","raw_affiliation_strings":["Chiba Institute of Technology,Chiba,Japan"],"affiliations":[{"raw_affiliation_string":"Chiba Institute of Technology,Chiba,Japan","institution_ids":["https://openalex.org/I8488066"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035657070","display_name":"Yoshiko Arimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I8488066","display_name":"Chiba Institute of Technology","ror":"https://ror.org/00qwnam72","country_code":"JP","type":"education","lineage":["https://openalex.org/I8488066"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiko Arimoto","raw_affiliation_strings":["Chiba Institute of Technology,Chiba,Japan"],"affiliations":[{"raw_affiliation_string":"Chiba Institute of Technology,Chiba,Japan","institution_ids":["https://openalex.org/I8488066"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5120437531"],"corresponding_institution_ids":["https://openalex.org/I8488066"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41256594,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"682","last_page":"687"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9495999813079834,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9495999813079834,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11795","display_name":"Humor Studies and Applications","score":0.01360000018030405,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.010200000368058681,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/laughter","display_name":"Laughter","score":0.9351999759674072},{"id":"https://openalex.org/keywords/screaming","display_name":"Screaming","score":0.6826000213623047},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4823000133037567},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.400299996137619},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3630000054836273},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.34459999203681946}],"concepts":[{"id":"https://openalex.org/C2780775679","wikidata":"https://www.wikidata.org/wiki/Q170579","display_name":"Laughter","level":2,"score":0.9351999759674072},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7192999720573425},{"id":"https://openalex.org/C2780778659","wikidata":"https://www.wikidata.org/wiki/Q1932016","display_name":"Screaming","level":2,"score":0.6826000213623047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.516700029373169},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3630000054836273},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C2988656282","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity detection","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C2781258422","wikidata":"https://www.wikidata.org/wiki/Q186819","display_name":"Headphones","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249388","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249388","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1970362344","https://openalex.org/W2040802023","https://openalex.org/W2065869176","https://openalex.org/W2169833301","https://openalex.org/W2397647387","https://openalex.org/W2610124020","https://openalex.org/W2750497738","https://openalex.org/W2962780374","https://openalex.org/W2972808026","https://openalex.org/W3081704551","https://openalex.org/W3096701465","https://openalex.org/W3148654612","https://openalex.org/W3197934793","https://openalex.org/W4211153864","https://openalex.org/W4296068599","https://openalex.org/W4296070362","https://openalex.org/W4372349820","https://openalex.org/W4375869369","https://openalex.org/W4385823281","https://openalex.org/W4400165401"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"investigated":[2],"the":[3,61,65,75,85,94,112,119,125,133,136],"effectiveness":[4],"of":[5,44,64,84,135],"realtime":[6],"laughter":[7,48,107,144],"and":[8,13,22,31,49,54,74,97,100,108,145],"screaming":[9,109],"detection":[10,45,104,110],"using":[11,26,33],"streaming":[12,21,66,90,137],"non-streaming":[14,23,86,113,126],"automatic":[15],"speech":[16,35,51,95,121],"recognition":[17,52,122],"(ASR)":[18],"models.":[19],"The":[20,37,57,89],"ASR":[24,67,87,91,114,127,138],"models":[25,39],"Transformer":[27],"architecture":[28],"were":[29,40],"trained":[30],"evaluated":[32],"spontaneous":[34],"corpora.":[36],"two":[38],"compared":[41],"in":[42,142],"terms":[43],"accuracies":[46,105],"for":[47,106],"screaming,":[50],"accuracy,":[53],"real-time":[55,62],"performance.":[56],"results":[58,130],"showed":[59],"that":[60,83,132],"factor":[63],"model":[68,92,139],"was":[69,77],"approximately":[70],"0.5":[71],"points":[72,102],"lower,":[73],"latency":[76],"about":[78],"0.3":[79],"s":[80],"shorter":[81],"than":[82,111],"model.":[88,128],"processed":[93],"faster":[96],"yielded":[98],"7":[99],"6":[101],"higher":[103],"model,":[115],"respectively,":[116],"while":[117],"yielding":[118],"same":[120],"accuracy":[123],"as":[124],"These":[129],"indicate":[131],"use":[134],"is":[140],"effective":[141],"detecting":[143],"screaming.":[146]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}