{"id":"https://openalex.org/W4411273550","doi":"https://doi.org/10.1186/s13636-025-00409-2","title":"ResCapsnet: a capsule network with CRAM and BiGRU for sound event detection","display_name":"ResCapsnet: a capsule network with CRAM and BiGRU for sound event detection","publication_year":2025,"publication_date":"2025-06-13","ids":{"openalex":"https://openalex.org/W4411273550","doi":"https://doi.org/10.1186/s13636-025-00409-2"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00409-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00409-2","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00409-2","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/s13636-025-00409-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016085650","display_name":"Bing Sun","orcid":"https://orcid.org/0000-0002-1432-6349"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Sun","raw_affiliation_strings":["College of Mathematics and Physics, Qingdao University of Science and Technology, Qingdao, 266061, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mathematics and Physics, Qingdao University of Science and Technology, Qingdao, 266061, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747209","display_name":"Chenglong Liu","orcid":"https://orcid.org/0000-0003-0728-1741"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Liu","raw_affiliation_strings":["College of Mathematics and Physics, Qingdao University of Science and Technology, Qingdao, 266061, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mathematics and Physics, Qingdao University of Science and Technology, Qingdao, 266061, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066428368","display_name":"Shuguo Yang","orcid":"https://orcid.org/0000-0003-3363-0044"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuguo Yang","raw_affiliation_strings":["College of Mathematics and Physics, Qingdao University of Science and Technology, Qingdao, 266061, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mathematics and Physics, Qingdao University of Science and Technology, Qingdao, 266061, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"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":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision Speech and Signal Processing (CVSSP), School of Computer Science and Electronic Engineering, University of Surrey, Guildford, GU2 7XH, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision Speech and Signal Processing (CVSSP), School of Computer Science and Electronic Engineering, University of Surrey, Guildford, GU2 7XH, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063573036","display_name":"Yiduo Mei","orcid":"https://orcid.org/0000-0002-5202-0033"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiduo Mei","raw_affiliation_strings":["Inspur Yunzhou Industrial Internet Co., Ltd., Jinan, 250101, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inspur Yunzhou Industrial Internet Co., Ltd., Jinan, 250101, China","institution_ids":["https://openalex.org/I4210144143"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.9024,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.72383422,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.879541277885437},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6833146810531616},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5492416024208069},{"id":"https://openalex.org/keywords/capsule","display_name":"Capsule","score":0.4382237493991852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43173766136169434},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4140547811985016},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3288644552230835},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.26104438304901123},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.10837963223457336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.879541277885437},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6833146810531616},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5492416024208069},{"id":"https://openalex.org/C2778778583","wikidata":"https://www.wikidata.org/wiki/Q147768","display_name":"Capsule","level":2,"score":0.4382237493991852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43173766136169434},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4140547811985016},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3288644552230835},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.26104438304901123},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.10837963223457336},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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":2,"locations":[{"id":"doi:10.1186/s13636-025-00409-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00409-2","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00409-2","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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:e27c616ae3c1438e93cbcb27fc9b5129","is_oa":true,"landing_page_url":"https://doaj.org/article/e27c616ae3c1438e93cbcb27fc9b5129","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-14 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00409-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00409-2","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00409-2","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411273550.pdf","grobid_xml":"https://content.openalex.org/works/W4411273550.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1970578576","https://openalex.org/W2064675550","https://openalex.org/W2097450352","https://openalex.org/W2109300274","https://openalex.org/W2120340098","https://openalex.org/W2131774270","https://openalex.org/W2143612262","https://openalex.org/W2164935924","https://openalex.org/W2168441989","https://openalex.org/W2194775991","https://openalex.org/W2341412280","https://openalex.org/W2407005679","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2604490051","https://openalex.org/W2735072998","https://openalex.org/W2746554716","https://openalex.org/W2775505379","https://openalex.org/W2797833340","https://openalex.org/W2810934215","https://openalex.org/W2883135409","https://openalex.org/W2897282582","https://openalex.org/W2942551338","https://openalex.org/W2959539607","https://openalex.org/W2962924597","https://openalex.org/W2963158330","https://openalex.org/W2963723765","https://openalex.org/W3006275583","https://openalex.org/W3082283760","https://openalex.org/W3098454764","https://openalex.org/W3158553615","https://openalex.org/W4206628220","https://openalex.org/W4221149441","https://openalex.org/W4324116353","https://openalex.org/W4372260505","https://openalex.org/W4389513749","https://openalex.org/W6600020421","https://openalex.org/W6604896550"],"related_works":["https://openalex.org/W2358162314","https://openalex.org/W2357652707","https://openalex.org/W2365313273","https://openalex.org/W2263516560","https://openalex.org/W2365750193","https://openalex.org/W2355255155","https://openalex.org/W4365513328","https://openalex.org/W2372963899","https://openalex.org/W2369519607","https://openalex.org/W2111187553"],"abstract_inverted_index":{"Sound":[0,162,174],"event":[1,202],"detection":[2,203],"(SED)":[3,204],"is":[4,108,144],"a":[5,15,88,95],"challenging":[6],"task":[7],"where":[8],"ambient":[9],"sound":[10,54,66,120,132,201],"events":[11,23,67,133],"are":[12,60,117,210],"detected":[13],"from":[14,68,113],"given":[16],"audio":[17],"signal,":[18],"which":[19],"includes":[20],"categorizing":[21],"the":[22,73,76,81,125,130,137,158,171,190,200],"and":[24,28,40,101,170,187,195,197],"estimating":[25],"their":[26,69],"onset":[27],"offset":[29],"times.":[30],"Deep":[31],"learning":[32,58],"methods":[33,59],"such":[34],"as":[35],"convolutional":[36],"neural":[37,42],"networks":[38,43],"(CNN)":[39],"recurrent":[41,104],"(RNN)":[44],"have":[45],"achieved":[46,183],"promising":[47],"performance":[48],"in":[49,63],"SED.":[50],"However,":[51],"for":[52],"overlapping":[53,131],"events,":[55],"existing":[56],"deep":[57],"still":[61],"limited":[62],"detecting":[64],"individual":[65],"mixtures.":[70],"Inspired":[71],"by":[72],"success":[74],"of":[75,80,185],"dynamic":[77,123],"routing":[78],"mechanism":[79],"capsule":[82,89,126],"network":[83,90,127],"(CapsNet),":[84],"this":[85],"paper":[86],"proposes":[87],"model":[91],"(ResCapsnet-BiGRU)":[92],"based":[93],"on":[94,155,189,199],"customized":[96],"residual":[97],"attention":[98],"module":[99],"(CRAM)":[100],"bidirectional":[102],"gated":[103],"unit":[105],"(BiGRU).":[106],"CRAM":[107],"utilized":[109],"to":[110,119,146],"extract":[111],"features":[112],"log-mel":[114],"spectrograms":[115],"that":[116],"relevant":[118],"events.":[121],"Through":[122],"routing,":[124],"can":[128],"address":[129],"problem.":[134],"In":[135],"addition,":[136],"BiGRU":[138],"with":[139],"time-distributed":[140],"fully":[141],"connected":[142],"layers":[143],"adopted":[145],"obtain":[147],"contextual":[148],"information.":[149],"Our":[150],"proposed":[151],"method":[152],"was":[153],"evaluated":[154],"two":[156],"datasets:":[157],"Vehicle":[159],"Weakly":[160],"Labeled":[161],"Dataset":[163,175],"(VWLSD":[164],",":[165,177],"DCASE":[166,178],"2017":[167],"Task":[168,180],"4)":[169],"Domestic":[172],"Environment":[173],"(DESD":[176],"2022":[179],"4).":[181],"It":[182],"F-scores":[184],"62.1%":[186],"75.9%":[188],"Audio":[191],"Tagging":[192],"(AT)":[193],"task,":[194,205],"54.1%":[196],"59.0%":[198],"respectively.":[206],"The":[207],"source":[208],"codes":[209],"available":[211],"at":[212],"https://github.com/123sunbing/ResCapsnet.git":[213],".":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}