{"id":"https://openalex.org/W4408355360","doi":"https://doi.org/10.1109/icassp49660.2025.10889807","title":"Global Enhanced Frame Prompt Tuning for Sound Event Detection","display_name":"Global Enhanced Frame Prompt Tuning for Sound Event Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355360","doi":"https://doi.org/10.1109/icassp49660.2025.10889807"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889807","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/A5101354051","display_name":"Shiyu Yu","orcid":"https://orcid.org/0009-0002-1697-2042"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyu Yu","raw_affiliation_strings":["Jiangsu University,School of Computer Science and Communication Engineering,Zhenjiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu University,School of Computer Science and Communication Engineering,Zhenjiang,China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008699574","display_name":"Lijian Gao","orcid":"https://orcid.org/0000-0002-6458-0660"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijian Gao","raw_affiliation_strings":["Jiangsu University,School of Computer Science and Communication Engineering,Zhenjiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu University,School of Computer Science and Communication Engineering,Zhenjiang,China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068470372","display_name":"Qirong Mao","orcid":"https://orcid.org/0000-0002-0616-4431"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qirong Mao","raw_affiliation_strings":["Jiangsu University,School of Computer Science and Communication Engineering,Zhenjiang,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu University,School of Computer Science and Communication Engineering,Zhenjiang,China","institution_ids":["https://openalex.org/I115592961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I115592961"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9952999949455261,"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":0.9922999739646912,"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/frame","display_name":"Frame (networking)","score":0.6663044691085815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6557141542434692},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6313304305076599},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5769109725952148},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3868890106678009},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3021485209465027},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.21080613136291504},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07923543453216553}],"concepts":[{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6663044691085815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557141542434692},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6313304305076599},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5769109725952148},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3868890106678009},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3021485209465027},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.21080613136291504},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07923543453216553},{"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/icassp49660.2025.10889807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889807","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":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5199999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321410","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30"},{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2959539607","https://openalex.org/W2966527417","https://openalex.org/W3160339728","https://openalex.org/W3185341429","https://openalex.org/W3203468141","https://openalex.org/W4200337780","https://openalex.org/W4205991051","https://openalex.org/W4221149441","https://openalex.org/W4224920041","https://openalex.org/W4304080535","https://openalex.org/W4312651322","https://openalex.org/W4315926819","https://openalex.org/W4372271592","https://openalex.org/W4385823043","https://openalex.org/W4385823229","https://openalex.org/W4386071848","https://openalex.org/W4392251904","https://openalex.org/W4392562716","https://openalex.org/W4392904244","https://openalex.org/W4393147969","https://openalex.org/W4401246677","https://openalex.org/W6733814495","https://openalex.org/W6778883912","https://openalex.org/W6848208918","https://openalex.org/W6870090694"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2025747832","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W611303608","https://openalex.org/W4313595395","https://openalex.org/W2312783472","https://openalex.org/W2909748163"],"abstract_inverted_index":{"Sound":[0],"Event":[1],"Detection":[2],"(SED)":[3],"often":[4],"employs":[5],"pre-trained":[6],"models":[7,20],"to":[8,78],"address":[9],"data":[10],"scarcity":[11],"issues.":[12],"However,":[13],"existing":[14],"systems":[15],"usually":[16],"treat":[17],"the":[18,32,43,131],"pretrained":[19,33,46],"as":[21],"frozen":[22],"feature":[23],"extractors,":[24],"resulting":[25],"in":[26,75,96],"suboptimal":[27],"efficiency,":[28],"or":[29],"fully":[30,41],"fine-tune":[31],"models,":[34,47],"which":[35,89],"requires":[36],"substantial":[37],"computational":[38,117],"resources.":[39],"To":[40],"leverage":[42],"knowledge":[44],"from":[45],"we":[48],"propose":[49],"a":[50],"novel":[51],"Global":[52],"Enhanced":[53],"Frame":[54,69],"Prompt":[55,70],"Tuning":[56,71],"(GE-FPT)":[57],"framework,":[58],"providing":[59],"global":[60],"and":[61,87,95],"local":[62,81],"insights":[63],"tailored":[64],"for":[65,92,98],"SED":[66,93],"tasks.":[67],"Additionally,":[68],"(FPT)":[72],"is":[73,90,139],"proposed":[74],"our":[76,107],"GE-FPT":[77],"effectively":[79],"explore":[80],"temporal":[82,85],"information,":[83],"i.e.,":[84],"details":[86],"context,":[88],"essential":[91],"tasks,":[94],"particular,":[97],"precise":[99],"event":[100],"boundary":[101],"detection.":[102],"Extensive":[103],"experiments":[104],"claim":[105],"that":[106],"approach":[108],"significantly":[109],"outperforms":[110],"full":[111],"fine-tuning":[112],"methods":[113],"while":[114],"substantially":[115],"reducing":[116],"costs.":[118],"Our":[119],"system":[120],"achieves":[121],"new":[122],"state-of-the-art":[123],"results,":[124],"with":[125],"PSDS1/PSDS2":[126],"scores":[127],"of":[128],"0.628/0.845":[129],"on":[130],"DCASE2023":[132],"Challenge":[133],"Task4":[134],"dataset.":[135],"The":[136],"source":[137],"code":[138],"publicly":[140],"available<sup":[141],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[142],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}