{"id":"https://openalex.org/W4411339348","doi":"https://doi.org/10.1186/s13636-025-00405-6","title":"Group feature calibration for sound event detection","display_name":"Group feature calibration for sound event detection","publication_year":2025,"publication_date":"2025-06-16","ids":{"openalex":"https://openalex.org/W4411339348","doi":"https://doi.org/10.1186/s13636-025-00405-6"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00405-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00405-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00405-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00405-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101499462","display_name":"Yanzhen Ren","orcid":"https://orcid.org/0000-0003-0799-5082"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanzhen Ren","raw_affiliation_strings":["Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, Wuhan, Hubei, 430072, China","School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, 430072, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, Wuhan, Hubei, 430072, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, 430072, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049058927","display_name":"Wuyang Liu","orcid":"https://orcid.org/0000-0003-2790-3069"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wuyang Liu","raw_affiliation_strings":["School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, 430072, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, 430072, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731340","display_name":"Chenyu Liu","orcid":"https://orcid.org/0000-0003-4290-1205"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyu Liu","raw_affiliation_strings":["School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, 430072, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, 430072, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055850985","display_name":"Tingting Zhu","orcid":"https://orcid.org/0000-0002-1552-5630"},"institutions":[{"id":"https://openalex.org/I2800710378","display_name":"Naval University of Engineering","ror":"https://ror.org/056vyez31","country_code":"CN","type":"education","lineage":["https://openalex.org/I2800710378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Zhu","raw_affiliation_strings":["Department of Information Security, Naval Engineering University, Wuhan, Hubei, 430033, China"],"affiliations":[{"raw_affiliation_string":"Department of Information Security, Naval Engineering University, Wuhan, Hubei, 430033, China","institution_ids":["https://openalex.org/I2800710378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101499462"],"corresponding_institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I37461747"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.5741,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82911985,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"2025","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9986000061035156,"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":0.9925000071525574,"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":0.8321077823638916},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6438586711883545},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6255775094032288},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.6092489957809448},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5736900568008423},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.514125406742096},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42736777663230896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4252516031265259},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2235155701637268},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10506939888000488},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08176010847091675},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0675879716873169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8321077823638916},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6438586711883545},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6255775094032288},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6092489957809448},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5736900568008423},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.514125406742096},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42736777663230896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4252516031265259},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2235155701637268},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10506939888000488},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08176010847091675},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0675879716873169},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00405-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00405-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00405-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ae0bcc9a61d040f387c91e6242588b3e","is_oa":true,"landing_page_url":"https://doaj.org/article/ae0bcc9a61d040f387c91e6242588b3e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-18 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00405-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00405-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00405-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3843378841","display_name":null,"funder_award_id":"NO.62172306 and NO. 61872275","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5618601050","display_name":null,"funder_award_id":"NO. 2021BAA034","funder_id":"https://openalex.org/F4320335792","funder_display_name":"Hubei Technological Innovation Special Fund"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6899305262","display_name":null,"funder_award_id":"2021BAA034","funder_id":"https://openalex.org/F4320335792","funder_display_name":"Hubei Technological Innovation Special Fund"},{"id":"https://openalex.org/G8184826122","display_name":null,"funder_award_id":"61872275","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8397513479","display_name":null,"funder_award_id":"62172306","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8955107213","display_name":null,"funder_award_id":"Major","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335792","display_name":"Hubei Technological Innovation Special Fund","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411339348.pdf","grobid_xml":"https://content.openalex.org/works/W4411339348.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2591013610","https://openalex.org/W2605646998","https://openalex.org/W2752782242","https://openalex.org/W2959539607","https://openalex.org/W2972612102","https://openalex.org/W3006275583","https://openalex.org/W3006560346","https://openalex.org/W3012740297","https://openalex.org/W3015190346","https://openalex.org/W3015594652","https://openalex.org/W3015805515","https://openalex.org/W3095753917","https://openalex.org/W3095994161","https://openalex.org/W3160339728","https://openalex.org/W3162400960","https://openalex.org/W3178592608","https://openalex.org/W3196645599","https://openalex.org/W3197014136","https://openalex.org/W3197827948","https://openalex.org/W4221149441","https://openalex.org/W4313118515","https://openalex.org/W4315926819","https://openalex.org/W4321192606","https://openalex.org/W4372270119","https://openalex.org/W6600704668","https://openalex.org/W6601174010"],"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":{"Abstract":[0],"Sound":[1,141],"Event":[2,142],"Detection":[3,143],"(SED)":[4],"is":[5,178],"a":[6,30,52],"pivotal":[7],"task":[8],"in":[9,32,133,170],"audio":[10],"signal":[11],"processing":[12],"with":[13,39,174],"widespread":[14],"applications,":[15],"requiring":[16],"the":[17,80,112,116,139,147,161,163,167,185,188,192],"classification":[18,38,104],"and":[19,74,85,89,105],"temporal":[20,43],"localization":[21],"of":[22,62,67,118,160,166,187],"sound":[23,63,91,172],"events.":[24,64],"However,":[25],"there":[26],"proves":[27],"to":[28,56,83,155],"be":[29],"challenge":[31],"balancing":[33],"global":[34,88],"features":[35,41],"for":[36,42],"event":[37,92,103],"local":[40,90],"localization.":[44,107],"This":[45,108],"paper":[46],"introduces":[47],"Group":[48,70],"Feature":[49,71],"Calibration":[50],"(GFC),":[51],"plug-and-play":[53],"solution":[54],"designed":[55],"effectively":[57,110],"representing":[58],"diverse":[59,175],"time-frequency":[60,176],"characteristics":[61,177],"GFC":[65,131,168,193],"consists":[66],"two":[68,124,189],"sub-modules:":[69],"Learning":[72],"(GFL)":[73],"Task-aware":[75],"Activation":[76],"(TA).":[77],"GFL":[78],"enhances":[79],"network\u2019s":[81],"ability":[82],"capture":[84],"integrate":[86],"both":[87,123],"features,":[93,113],"while":[94],"TA":[95],"adaptively":[96],"refines":[97],"feature":[98],"activation,":[99],"facilitating":[100],"more":[101],"precise":[102],"time":[106],"approach":[109],"recalibrates":[111],"significantly":[114],"improving":[115],"performance":[117],"various":[119],"SED":[120,136],"models":[121],"on":[122,146],"sub-tasks.":[125],"Experimental":[126],"results":[127],"demonstrate":[128],"that":[129],"implementing":[130],"module":[132,169],"three":[134],"mainstream":[135],"networks":[137],"improves":[138],"Polyphonic":[140],"Score":[144],"(PSDS)":[145],"DCASE":[148],"2022":[149],"Task":[150],"4":[151],"dataset":[152],"by":[153],"up":[154],"9.94%.":[156],"Through":[157],"class-wise":[158],"analysis":[159],"results,":[162],"consistent":[164],"improvement":[165],"detecting":[171],"events":[173],"proven.":[179],"Further":[180],"ablation":[181],"study":[182],"also":[183],"validates":[184],"effectiveness":[186],"sub-modules":[190],"within":[191],"module.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}