{"id":"https://openalex.org/W4408354509","doi":"https://doi.org/10.1109/icassp49660.2025.10888080","title":"Unified Audio Event Detection","display_name":"Unified Audio Event Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354509","doi":"https://doi.org/10.1109/icassp49660.2025.10888080"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5016187230","display_name":"Yidi Jiang","orcid":"https://orcid.org/0000-0001-9013-0869"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yidi Jiang","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026034735","display_name":"Ruijie Tao","orcid":"https://orcid.org/0000-0003-0021-5661"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ruijie Tao","raw_affiliation_strings":["National University of Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045255566","display_name":"Wen Huang","orcid":"https://orcid.org/0000-0002-8721-6474"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Huang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428456","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0002-1909-302X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115592093","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0001-8392-3457"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Tongyi Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongyi Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.5391,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97413883,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9296000003814697,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9179999828338623,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.704646646976471},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5262024998664856},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36993083357810974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.704646646976471},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5262024998664856},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36993083357810974},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2153842971","https://openalex.org/W2408239454","https://openalex.org/W2593116425","https://openalex.org/W2959539607","https://openalex.org/W2972449503","https://openalex.org/W2972949456","https://openalex.org/W3015190346","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3095212884","https://openalex.org/W3178592608","https://openalex.org/W3209984917","https://openalex.org/W4224920041","https://openalex.org/W4372263379","https://openalex.org/W4372267289","https://openalex.org/W4372340947","https://openalex.org/W4375868885","https://openalex.org/W4385245566","https://openalex.org/W4385822749","https://openalex.org/W4391892525","https://openalex.org/W4392904244","https://openalex.org/W4392909895","https://openalex.org/W4404781855","https://openalex.org/W4408352172","https://openalex.org/W4408353947","https://openalex.org/W6759579507","https://openalex.org/W6779069803","https://openalex.org/W6848208918","https://openalex.org/W6869055001","https://openalex.org/W6873871726"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Sound":[0],"Event":[1,72],"Detection":[2,73],"(SED)":[3],"detects":[4],"regions":[5],"of":[6,145],"sound":[7,91],"events,":[8],"while":[9,32],"Speaker":[10],"Diarization":[11],"(SD)":[12],"segments":[13,24],"speech":[14,30,56,95],"conversations":[15],"attributed":[16],"to":[17,158],"individual":[18,162],"speakers.":[19],"In":[20,61],"SED,":[21],"all":[22],"speaker":[23,99],"are":[25,37],"classified":[26],"as":[27,40],"a":[28,66,107],"single":[29],"event,":[31],"in":[33,50],"SD,":[34],"non-speech":[35,59,90],"sounds":[36],"treated":[38],"merely":[39],"background":[41],"noise.":[42],"Thus,":[43],"both":[44,55],"tasks":[45,166],"provide":[46],"only":[47],"partial":[48],"analysis":[49],"complex":[51],"audio":[52,77],"scenarios":[53],"involving":[54],"conversation":[57],"and":[58,85,93,112,122,135,147,164,169],"sounds.":[60],"this":[62,103],"paper,":[63],"we":[64,105],"introduce":[65],"novel":[67],"task":[68,133],"called":[69],"Unified":[70],"Audio":[71],"(UAED)":[74],"for":[75,161],"comprehensive":[76],"analysis.":[78],"UAED":[79,109,115],"explores":[80],"the":[81,114,119,128,138,143],"synergy":[82],"between":[83],"SED":[84,146,163],"SD":[86,148,165],"tasks,":[87],"simultaneously":[88],"detecting":[89],"events":[92,96],"fine-grained":[94],"based":[97],"on":[98,167],"identities.":[100],"To":[101],"tackle":[102],"task,":[104],"propose":[106],"Transformer-based":[108],"(T-UAED)":[110],"framework":[111,130],"construct":[113],"Data":[116],"derived":[117],"from":[118],"Librispeech":[120],"dataset":[121],"DESED":[123,168],"soundbank.":[124],"Experiments":[125],"demonstrate":[126],"that":[127,140],"proposed":[129],"effectively":[131],"exploits":[132],"interactions":[134],"substantially":[136],"outperforms":[137],"baseline":[139],"simply":[141],"combines":[142],"outputs":[144],"models.":[149],"T-UAED":[150],"also":[151],"shows":[152],"its":[153],"versatility":[154],"by":[155],"performing":[156],"comparably":[157],"specialized":[159],"models":[160],"CALLHOME":[170],"datasets.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
