{"id":"https://openalex.org/W4416798834","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249157","title":"Time-Aligned Laughter Sound Event Recognition for Conversational Laughter Analysis and Synthesis","display_name":"Time-Aligned Laughter Sound Event Recognition for Conversational Laughter Analysis and Synthesis","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798834","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249157"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249157","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/A5101591500","display_name":"Hiroki Mori","orcid":"https://orcid.org/0000-0002-2883-1143"},"institutions":[{"id":"https://openalex.org/I207399273","display_name":"Utsunomiya University","ror":"https://ror.org/05bx1gz93","country_code":"JP","type":"education","lineage":["https://openalex.org/I207399273"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiroki Mori","raw_affiliation_strings":["Utsunomiya University,Japan"],"affiliations":[{"raw_affiliation_string":"Utsunomiya University,Japan","institution_ids":["https://openalex.org/I207399273"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101591500"],"corresponding_institution_ids":["https://openalex.org/I207399273"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38607215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1134","last_page":"1139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.7131999731063843,"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":0.7131999731063843,"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":0.11949999630451202,"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/T11309","display_name":"Music and Audio Processing","score":0.043699998408555984,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/laughter","display_name":"Laughter","score":0.9401999711990356},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5235999822616577},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5065000057220459},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4397999942302704},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4147000014781952},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.41350001096725464}],"concepts":[{"id":"https://openalex.org/C2780775679","wikidata":"https://www.wikidata.org/wiki/Q170579","display_name":"Laughter","level":2,"score":0.9401999711990356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6877999901771545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6439999938011169},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35920000076293945},{"id":"https://openalex.org/C3018392663","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Speech sound","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.2648000121116638}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249157","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":[{"id":"https://openalex.org/G4713052181","display_name":null,"funder_award_id":"22K12107,22K18477","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W69338719","https://openalex.org/W187812487","https://openalex.org/W1964184389","https://openalex.org/W1969761120","https://openalex.org/W1970362344","https://openalex.org/W2044315228","https://openalex.org/W2087779800","https://openalex.org/W2100056961","https://openalex.org/W2103493245","https://openalex.org/W2117712320","https://openalex.org/W2141814871","https://openalex.org/W2570199661","https://openalex.org/W2747874407","https://openalex.org/W2973149295","https://openalex.org/W3096701465","https://openalex.org/W3196971969","https://openalex.org/W4372271612","https://openalex.org/W4385823467","https://openalex.org/W4392902865"],"related_works":[],"abstract_inverted_index":{"Although":[0],"time-aligned":[1],"laughter":[2,13,20,31,65],"data":[3],"is":[4,26],"essential":[5],"for":[6,19,115],"various":[7],"studies":[8],"including":[9],"phonetics":[10],"and":[11,23],"conversational":[12],"synthesis,":[14],"existing":[15,36],"corpora":[16],"lack":[17],"annotations":[18],"sound":[21,66],"events,":[22],"manual":[24],"annotation":[25],"highly":[27],"costly.":[28],"Accurately":[29],"recognizing":[30],"components":[32],"remains":[33],"challenging":[34],"with":[35],"speech":[37],"recognition":[38,68,98],"models.":[39],"In":[40],"particular,":[41],"the":[42,81,86,104,120],"conventional":[43,121],"CTCbased":[44,122],"approach":[45,123],"fails":[46],"to":[47,96,127],"effectively":[48],"utilize":[49],"temporal":[50],"information,":[51],"resulting":[52],"in":[53,85],"poor":[54],"boundary":[55,82,109],"estimation":[56],"accuracy.":[57,99],"To":[58],"address":[59],"this":[60],"issue,":[61],"we":[62],"propose":[63],"a":[64,92],"event":[67],"model":[69],"that":[70,103],"minimizes":[71],"frame-wise":[72],"loss":[73,77],"instead":[74],"of":[75,112],"CTC":[76],"while":[78],"fully":[79],"leveraging":[80],"information":[83],"provided":[84],"training":[87],"dataset.":[88],"We":[89],"also":[90],"introduce":[91],"new":[93],"evaluation":[94],"metric":[95],"assess":[97],"Experimental":[100],"results":[101],"demonstrate":[102],"proposed":[105],"method":[106],"achieves":[107],"phone":[108],"errors":[110],"(PBE)":[111],"16.8":[113],"ms":[114],"seen":[116],"speakers,":[117],"significantly":[118],"outperforming":[119],"by":[124],"reducing":[125],"PBE":[126],"approximately":[128],"one-fifth.":[129]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}