{"id":"https://openalex.org/W4387264797","doi":"https://doi.org/10.3390/info14100534","title":"Sound Event Detection in Domestic Environment Using Frequency-Dynamic Convolution and Local Attention","display_name":"Sound Event Detection in Domestic Environment Using Frequency-Dynamic Convolution and Local Attention","publication_year":2023,"publication_date":"2023-09-30","ids":{"openalex":"https://openalex.org/W4387264797","doi":"https://doi.org/10.3390/info14100534"},"language":"en","primary_location":{"id":"doi:10.3390/info14100534","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info14100534","pdf_url":"https://www.mdpi.com/2078-2489/14/10/534/pdf?version=1696054093","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/14/10/534/pdf?version=1696054093","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020705965","display_name":"Grigorios\u2010Aris Cheimariotis","orcid":"https://orcid.org/0000-0003-1984-5030"},"institutions":[{"id":"https://openalex.org/I147962203","display_name":"Democritus University of Thrace","ror":"https://ror.org/03bfqnx40","country_code":"GR","type":"education","lineage":["https://openalex.org/I147962203"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Grigorios-Aris Cheimariotis","raw_affiliation_strings":["Electrical and Computer Engineering Department, Democritus University of Thrace, 67100 Xanthi, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Democritus University of Thrace, 67100 Xanthi, Greece","institution_ids":["https://openalex.org/I147962203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064706177","display_name":"Nikolaos Mitianoudis","orcid":"https://orcid.org/0000-0003-0898-6102"},"institutions":[{"id":"https://openalex.org/I147962203","display_name":"Democritus University of Thrace","ror":"https://ror.org/03bfqnx40","country_code":"GR","type":"education","lineage":["https://openalex.org/I147962203"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Nikolaos Mitianoudis","raw_affiliation_strings":["Electrical and Computer Engineering Department, Democritus University of Thrace, 67100 Xanthi, Greece"],"raw_orcid":"https://orcid.org/0000-0003-0898-6102","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Democritus University of Thrace, 67100 Xanthi, Greece","institution_ids":["https://openalex.org/I147962203"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064706177"],"corresponding_institution_ids":["https://openalex.org/I147962203"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.1233,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78801586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"14","issue":"10","first_page":"534","last_page":"534"},"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":0.9724000096321106,"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/spectrogram","display_name":"Spectrogram","score":0.8982977867126465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.724890410900116},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.723008394241333},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.616611659526825},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5998092889785767},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5779088139533997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5414168834686279},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5126048922538757},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4658428430557251},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4641486406326294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38691115379333496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14105018973350525},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11036178469657898},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10145431756973267}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8982977867126465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.724890410900116},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.723008394241333},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.616611659526825},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5998092889785767},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5779088139533997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5414168834686279},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5126048922538757},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4658428430557251},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4641486406326294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38691115379333496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14105018973350525},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11036178469657898},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10145431756973267},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info14100534","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info14100534","pdf_url":"https://www.mdpi.com/2078-2489/14/10/534/pdf?version=1696054093","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6ad7525d91a3438da0c9446d72558a6b","is_oa":true,"landing_page_url":"https://doaj.org/article/6ad7525d91a3438da0c9446d72558a6b","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":"Information, Vol 14, Iss 10, p 534 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2078-2489/14/10/534/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/info14100534","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/info14100534","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info14100534","pdf_url":"https://www.mdpi.com/2078-2489/14/10/534/pdf?version=1696054093","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G1337233005","display_name":null,"funder_award_id":"NSRF 2014-2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2881834948","display_name":null,"funder_award_id":"MIS 5047294","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G5634946813","display_name":null,"funder_award_id":"2014-2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6870533126","display_name":null,"funder_award_id":"2014-2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7538097724","display_name":null,"funder_award_id":"NSRF 2014-2020","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387264797.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2104956067","https://openalex.org/W2130103019","https://openalex.org/W2157331557","https://openalex.org/W2296193698","https://openalex.org/W2593116425","https://openalex.org/W2953070460","https://openalex.org/W3006275583","https://openalex.org/W3015190346","https://openalex.org/W3097777922","https://openalex.org/W3160339728","https://openalex.org/W3201143670","https://openalex.org/W3203468141","https://openalex.org/W3205743929","https://openalex.org/W4214612132","https://openalex.org/W4214835877","https://openalex.org/W4221149441","https://openalex.org/W4224920041","https://openalex.org/W4226442948","https://openalex.org/W4296068822","https://openalex.org/W4313175917","https://openalex.org/W4375868802","https://openalex.org/W4382461973","https://openalex.org/W4385346076","https://openalex.org/W6733814495","https://openalex.org/W6757817989","https://openalex.org/W6847573028"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2011227383","https://openalex.org/W2373577936","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W4221148444","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W3179495260"],"abstract_inverted_index":{"This":[0,54,143],"work":[1],"describes":[2],"a":[3,104,133,184],"methodology":[4,26,87],"for":[5,129,139],"sound":[6,69,96],"event":[7,49],"detection":[8,50,58],"in":[9,14,63,66,77,113,177,181],"domestic":[10,52,64],"environments.":[11],"Efficient":[12],"solutions":[13],"this":[15],"task":[16,55],"can":[17],"support":[18],"the":[19,23,29,57,78,86,95,147,154,166],"autonomous":[20],"living":[21],"of":[22,35,51,59,85,119,127,149,153],"elderly.":[24],"The":[25,71,82,162,192],"deals":[27],"with":[28,45,108,115,122,183],"\u201cChallenge":[30],"on":[31,91,146,159,175],"Detection":[32],"and":[33,38,42,125,158,197],"Classification":[34],"Acoustic":[36],"Scenes":[37],"Events":[39],"(DCASE)\u201d":[40],"2023,":[41],"more":[43],"specifically":[44],"Task":[46],"4a":[47],"\u201cSound":[48],"activities\u201d.":[53],"involves":[56],"10":[60,67,79],"common":[61],"events":[62,72],"environments":[65],"s":[68,80],"clips.":[70],"may":[73],"have":[74],"arbitrary":[75],"duration":[76],"clip.":[81],"main":[83,163],"components":[84],"are":[88],"data":[89,150],"augmentation":[90,151],"mel-spectrograms":[92],"that":[93],"represent":[94],"clips,":[97],"feature":[98,155,168],"extraction":[99,156,169],"by":[100,189],"passing":[101],"spectrograms":[102],"through":[103],"frequency-dynamic":[105],"convolution":[106],"network":[107],"an":[109],"extra":[110],"attention":[111,174,186],"module":[112,187],"sequence":[114,130,182],"each":[116,178],"convolution,":[117,179],"concatenation":[118],"these":[120],"features":[121,195],"BEATs":[123],"embeddings,":[124],"use":[126],"BiGRU":[128],"modeling.":[131],"Also,":[132],"mean":[134],"teacher":[135],"model":[136],"is":[137,165],"employed":[138],"leveraging":[140],"unlabeled":[141],"data.":[142],"research":[144],"focuses":[145],"effect":[148],"techniques,":[152],"models,":[157],"self-supervised":[160],"learning.":[161],"contribution":[164],"proposed":[167,193],"model,":[170],"which":[171],"uses":[172],"weighted":[173],"frequency":[176],"combined":[180],"local":[185],"adopted":[188],"computer":[190],"vision.":[191],"system":[194],"promising":[196],"robust":[198],"performance.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
