{"id":"https://openalex.org/W4416251548","doi":"https://doi.org/10.1109/waspaa66052.2025.11230975","title":"FlexSED: Towards Open-Vocabulary Sound Event Detection","display_name":"FlexSED: Towards Open-Vocabulary Sound Event Detection","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416251548","doi":"https://doi.org/10.1109/waspaa66052.2025.11230975"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5048171604","display_name":"Jiarui Hai","orcid":"https://orcid.org/0000-0001-9968-7372"},"institutions":[{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiarui Hai","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA","institution_ids":["https://openalex.org/I2802946424","https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664824","display_name":"Helin Wang","orcid":"https://orcid.org/0000-0001-6088-0378"},"institutions":[{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Helin Wang","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA","institution_ids":["https://openalex.org/I2802946424","https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101238550","display_name":"Weizhe Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weizhe Guo","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA","institution_ids":["https://openalex.org/I2802946424","https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038788686","display_name":"Mounya Elhilali","orcid":"https://orcid.org/0000-0003-2597-738X"},"institutions":[{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mounya Elhilali","raw_affiliation_strings":["Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Department of Electrical and Computer Engineering,Maryland,USA","institution_ids":["https://openalex.org/I2802946424","https://openalex.org/I145311948","https://openalex.org/I2799853436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048171604"],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2799853436","https://openalex.org/I2802946424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45504645,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.8917999863624573,"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":0.8917999863624573,"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":0.05620000138878822,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.02630000002682209,"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/event","display_name":"Event (particle physics)","score":0.6671000123023987},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5999000072479248},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5331000089645386},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.44530001282691956},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4320000112056732},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.38999998569488525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613999843597412},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6671000123023987},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5999000072479248},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5331000089645386},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.44530001282691956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4438999891281128},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4198000133037567},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3203999996185303},{"id":"https://openalex.org/C2984030306","wikidata":"https://www.wikidata.org/wiki/Q4819857","display_name":"Sound analysis","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":22,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2936774411","https://openalex.org/W2959539607","https://openalex.org/W3015190346","https://openalex.org/W3162999565","https://openalex.org/W3173859428","https://openalex.org/W3178592608","https://openalex.org/W3203468141","https://openalex.org/W4221149441","https://openalex.org/W4224920041","https://openalex.org/W4372260310","https://openalex.org/W4386047807","https://openalex.org/W4390738640","https://openalex.org/W4390872297","https://openalex.org/W4392904244","https://openalex.org/W4402112407","https://openalex.org/W4404784428","https://openalex.org/W4405934446","https://openalex.org/W4408351785","https://openalex.org/W4408353596","https://openalex.org/W4408353947","https://openalex.org/W4415433415"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"recent":[1],"progress":[2],"in":[3,135],"large-scale":[4],"sound":[5,15,28,78,88],"event":[6,89,136],"detection":[7,73,90],"(SED)":[8],"systems":[9],"capable":[10],"of":[11,14],"handling":[12],"hundreds":[13],"classes,":[16],"existing":[17],"multi-class":[18],"classification":[19],"frameworks":[20],"remain":[21],"fundamentally":[22],"limited.":[23],"They":[24],"cannot":[25],"process":[26],"free-text":[27],"queries,":[29],"which":[30],"enable":[31,115],"more":[32],"flexible":[33],"and":[34,37,42,60,71,76,100,109,165,172,179],"user-friendly":[35],"interaction,":[36],"they":[38,54],"lack":[39],"zero-shot":[40,164],"capabilities":[41],"offer":[43],"poor":[44],"few-shot":[45,166],"adaptability.":[46],"Although":[47],"text-query-based":[48],"separation":[49,59],"methods":[50],"have":[51],"been":[52],"explored,":[53],"primarily":[55],"focus":[56],"on":[57,94,159,182],"source":[58],"are":[61],"ill-suited":[62],"for":[63],"SED":[64,157],"tasks":[65],"that":[66],"require":[67],"precise":[68],"temporal":[69],"localization":[70],"efficient":[72],"across":[74],"large":[75,129],"diverse":[77],"vocabularies.":[79],"In":[80],"this":[81],"paper,":[82],"we":[83],"propose":[84],"FlexSED,":[85],"an":[86,106,110],"open-vocabulary":[87],"system.":[91],"FlexSED":[92,150],"builds":[93],"a":[95,148],"pretrained":[96,120,173],"audio":[97],"SSL":[98],"model":[99],"the":[101,170],"CLAP":[102],"text":[103],"encoder,":[104],"introducing":[105],"encoder-decoder":[107],"composition":[108],"adaptive":[111],"fusion":[112],"strategy":[113],"to":[114,133,144,155,175],"effective":[116],"continuous":[117],"training":[118],"from":[119],"weights.":[121],"To":[122],"ensure":[123],"robust":[124],"supervision,":[125],"it":[126],"also":[127],"employs":[128],"language":[130],"models":[131,158,174],"(LLMs)":[132],"assist":[134],"query":[137],"selection":[138],"during":[139],"training,":[140],"addressing":[141],"challenges":[142],"related":[143],"missing":[145],"labels.":[146],"As":[147],"result,":[149],"achieves":[151],"superior":[152],"performance":[153],"compared":[154],"vanilla":[156],"AudioSet-Strong,":[160],"while":[161],"demonstrating":[162],"strong":[163],"capabilities.":[167],"We":[168],"release":[169],"code":[171],"support":[176],"future":[177],"research":[178],"applications":[180],"based":[181],"FlexSED.":[183]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}