{"id":"https://openalex.org/W7083285386","doi":"https://doi.org/10.1109/lsp.2025.3614476","title":"Noise-Robust Sound Event Detection and Counting via Language-Queried Sound Separation","display_name":"Noise-Robust Sound Event Detection and Counting via Language-Queried Sound Separation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7083285386","doi":"https://doi.org/10.1109/lsp.2025.3614476"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3614476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3614476","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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":null,"display_name":"Yuanjian Chen","orcid":"https://orcid.org/0000-0003-0718-7405"},"institutions":[{"id":"https://openalex.org/I100188998","display_name":"Harbin University of Science and Technology","ror":"https://ror.org/04e6y1282","country_code":"CN","type":"education","lineage":["https://openalex.org/I100188998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanjian Chen","raw_affiliation_strings":["School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-0718-7405","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China","institution_ids":["https://openalex.org/I100188998"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yang Xiao","raw_affiliation_strings":["University of Melbourne, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Han Yin","orcid":"https://orcid.org/0009-0008-9413-1859"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Han Yin","raw_affiliation_strings":["School of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0009-0008-9413-1859","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yadong Guan","orcid":"https://orcid.org/0009-0002-6031-9892"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Guan","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0002-6031-9892","affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xubo Liu","orcid":"https://orcid.org/0009-0004-9950-2672"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guilford, U.K"],"raw_orcid":"https://orcid.org/0009-0004-9950-2672","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guilford, U.K","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48776139,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"3974","last_page":"3978"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6280999779701233,"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/T10860","display_name":"Speech and Audio Processing","score":0.6280999779701233,"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/T11309","display_name":"Music and Audio Processing","score":0.34940001368522644,"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":0.004800000227987766,"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/timestamp","display_name":"Timestamp","score":0.7440000176429749},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6360999941825867},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6105999946594238},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5205000042915344},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5128999948501587},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4887999892234802},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.484499990940094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4609000086784363},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4359999895095825}],"concepts":[{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.7440000176429749},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401000261306763},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6360999941825867},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6105999946594238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5242999792098999},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4887999892234802},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.484499990940094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44339999556541443},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4359999895095825},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4343000054359436},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4291999936103821},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3156999945640564},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2964000105857849},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.28690001368522644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28279998898506165},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.271699994802475},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2669999897480011},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3614476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3614476","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2826982024","display_name":null,"funder_award_id":"62206258","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W821549425","https://openalex.org/W1970578576","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2734691436","https://openalex.org/W2798158991","https://openalex.org/W2959539607","https://openalex.org/W3015190346","https://openalex.org/W3049446265","https://openalex.org/W3160845765","https://openalex.org/W3176411119","https://openalex.org/W3185940864","https://openalex.org/W4213366994","https://openalex.org/W4221149441","https://openalex.org/W4233392025","https://openalex.org/W4293558655","https://openalex.org/W4296121022","https://openalex.org/W4297841355","https://openalex.org/W4313061427","https://openalex.org/W4389117036","https://openalex.org/W4392251904","https://openalex.org/W4392904244","https://openalex.org/W4392904741","https://openalex.org/W4393147524","https://openalex.org/W4393158264","https://openalex.org/W4396605323","https://openalex.org/W4401990901","https://openalex.org/W4403063533","https://openalex.org/W4405934446","https://openalex.org/W4408352174","https://openalex.org/W4408353947","https://openalex.org/W4408355302","https://openalex.org/W4410779772"],"related_works":[],"abstract_inverted_index":{"Most":[0],"sound":[1],"event":[2,51,60],"detection":[3,53,127],"(SED)":[4],"systems":[5],"perform":[6],"well":[7],"on":[8,70,130],"clean":[9],"datasets":[10,134],"but":[11],"degraded":[12],"significantly":[13],"in":[14,87],"noisy":[15,88],"environments.":[16,89],"Language-queried":[17],"audio":[18],"source":[19],"separation":[20],"(LASS)":[21],"models":[22,123],"show":[23],"promise":[24],"for":[25,42,79,121],"robust":[26],"SED":[27,82,91,111],"by":[28],"separating":[29],"target":[30,43],"events,":[31],"existing":[32,140],"methods":[33],"require":[34],"elaborate":[35],"multi-stage":[36],"training":[37],"and":[38,66,81,112,124,132],"lack":[39],"explicit":[40],"guidance":[41],"events.":[44],"To":[45],"address":[46],"these":[47],"challenges,":[48],"we":[49,72],"introduce":[50,73],"appearance":[52],"(EAD),":[54],"a":[55,74,101],"counting-based":[56],"manner":[57],"that":[58],"counts":[59],"occurrences":[61],"at":[62,147],"both":[63],"the":[64,95],"clip":[65],"frame":[67],"levels.":[68,150],"Based":[69],"EAD,":[71],"co-training\u2013based":[75],"multi-task":[76],"learning":[77],"framework":[78,115],"EAD":[80],"to":[83,93,106,139],"enhance":[84],"SED's":[85],"performance":[86,137],"First,":[90],"struggles":[92],"learn":[94],"same":[96],"pattern":[97],"as":[98],"EAD.":[99,113],"Then,":[100],"task-based":[102],"constraint":[103],"is":[104,153],"designed":[105],"improve":[107],"prediction":[108],"consistency":[109],"between":[110],"This":[114],"provides":[116],"more":[117,145],"reliable":[118],"clip-level":[119],"predictions":[120],"LASS":[122],"strengthen":[125],"timestamps":[126],"capability.":[128],"Experiments":[129],"DESED":[131],"WildDESED":[133],"demonstrate":[135],"better":[136],"compared":[138],"methods,":[141],"with":[142],"advantages":[143],"becoming":[144],"pronounced":[146],"higher":[148],"noise":[149],"The":[151],"code":[152],"available":[154],"at:":[155],"<uri":[156],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/visionchan/EADSED</uri>.":[158]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}