{"id":"https://openalex.org/W4401685421","doi":"https://doi.org/10.3390/s24165336","title":"A Study of Improved Two-Stage Dual-Conv Coordinate Attention Model for Sound Event Detection and Localization","display_name":"A Study of Improved Two-Stage Dual-Conv Coordinate Attention Model for Sound Event Detection and Localization","publication_year":2024,"publication_date":"2024-08-18","ids":{"openalex":"https://openalex.org/W4401685421","doi":"https://doi.org/10.3390/s24165336","pmid":"https://pubmed.ncbi.nlm.nih.gov/39205033"},"language":"en","primary_location":{"id":"doi:10.3390/s24165336","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24165336","pdf_url":"https://www.mdpi.com/1424-8220/24/16/5336/pdf?version=1723967934","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"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":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/24/16/5336/pdf?version=1723967934","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101543487","display_name":"Guorong Chen","orcid":"https://orcid.org/0009-0008-7186-7417"},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guorong Chen","raw_affiliation_strings":["School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, No. 20, Daxuecheng East Road, Shapingba District, Chongqing 401331, China"],"raw_orcid":"https://orcid.org/0009-0008-7186-7417","affiliations":[{"raw_affiliation_string":"School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, No. 20, Daxuecheng East Road, Shapingba District, Chongqing 401331, China","institution_ids":["https://openalex.org/I168337820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101559700","display_name":"Yu Yuan","orcid":"https://orcid.org/0009-0007-2664-9413"},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuan Yu","raw_affiliation_strings":["School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, No. 20, Daxuecheng East Road, Shapingba District, Chongqing 401331, China"],"raw_orcid":"https://orcid.org/0009-0007-2664-9413","affiliations":[{"raw_affiliation_string":"School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, No. 20, Daxuecheng East Road, Shapingba District, Chongqing 401331, China","institution_ids":["https://openalex.org/I168337820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086103184","display_name":"Yuan Qiao","orcid":"https://orcid.org/0000-0002-1100-634X"},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Qiao","raw_affiliation_strings":["School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, No. 20, Daxuecheng East Road, Shapingba District, Chongqing 401331, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, No. 20, Daxuecheng East Road, Shapingba District, Chongqing 401331, China","institution_ids":["https://openalex.org/I168337820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115588181","display_name":"Junliang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junliang Yang","raw_affiliation_strings":["School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, No. 20, Daxuecheng East Road, Shapingba District, Chongqing 401331, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, No. 20, Daxuecheng East Road, Shapingba District, Chongqing 401331, China","institution_ids":["https://openalex.org/I168337820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112943483","display_name":"Chongling Du","orcid":null},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongling Du","raw_affiliation_strings":["School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, No. 20, Daxuecheng East Road, Shapingba District, Chongqing 401331, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, No. 20, Daxuecheng East Road, Shapingba District, Chongqing 401331, China","institution_ids":["https://openalex.org/I168337820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106600538","display_name":"Qian Zhang","orcid":"https://orcid.org/0009-0003-8787-1043"},"institutions":[{"id":"https://openalex.org/I168337820","display_name":"Chongqing University of Science and Technology","ror":"https://ror.org/03n3v6d52","country_code":"CN","type":"education","lineage":["https://openalex.org/I168337820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Qian","raw_affiliation_strings":["School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, No. 20, Daxuecheng East Road, Shapingba District, Chongqing 401331, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligent Technology and Engineering, Chongqing University of Science and Technology, No. 20, Daxuecheng East Road, Shapingba District, Chongqing 401331, China","institution_ids":["https://openalex.org/I168337820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055037545","display_name":"Xiao Huang","orcid":"https://orcid.org/0000-0002-3867-900X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiao Huang","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR 999077, China"],"raw_orcid":"https://orcid.org/0000-0002-3867-900X","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR 999077, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101543487","https://openalex.org/A5101559700"],"corresponding_institution_ids":["https://openalex.org/I168337820"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":1.0764,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75712821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"24","issue":"16","first_page":"5336","last_page":"5336"},"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":0.9987999796867371,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6930476427078247},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5195744037628174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5001170635223389},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.46148672699928284},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44640469551086426},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4420914351940155},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4224853515625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13270515203475952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930476427078247},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5195744037628174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5001170635223389},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.46148672699928284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44640469551086426},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4420914351940155},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4224853515625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13270515203475952},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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":4,"locations":[{"id":"doi:10.3390/s24165336","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24165336","pdf_url":"https://www.mdpi.com/1424-8220/24/16/5336/pdf?version=1723967934","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"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":"Sensors","raw_type":"journal-article"},{"id":"pmid:39205033","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39205033","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11359102","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11359102","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11359102/pdf/sensors-24-05336.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:eeb3b677ce764ca886ec72137175c18a","is_oa":true,"landing_page_url":"https://doaj.org/article/eeb3b677ce764ca886ec72137175c18a","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":"Sensors, Vol 24, Iss 16, p 5336 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/s24165336","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24165336","pdf_url":"https://www.mdpi.com/1424-8220/24/16/5336/pdf?version=1723967934","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"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":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401685421.pdf","grobid_xml":"https://content.openalex.org/works/W4401685421.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1972567154","https://openalex.org/W2008750120","https://openalex.org/W2046317813","https://openalex.org/W2103235956","https://openalex.org/W2113744809","https://openalex.org/W2127448212","https://openalex.org/W2132083787","https://openalex.org/W2222512263","https://openalex.org/W2292996718","https://openalex.org/W2341412280","https://openalex.org/W2408239454","https://openalex.org/W2640418943","https://openalex.org/W2772736377","https://openalex.org/W2803878161","https://openalex.org/W2810934215","https://openalex.org/W2936774411","https://openalex.org/W2942551338","https://openalex.org/W2964342924","https://openalex.org/W2982382207","https://openalex.org/W2982549770","https://openalex.org/W3098454764","https://openalex.org/W3105684258","https://openalex.org/W3119841144","https://openalex.org/W3129524875","https://openalex.org/W3177052299","https://openalex.org/W4382787045","https://openalex.org/W4385626247","https://openalex.org/W4390703097","https://openalex.org/W4390754202","https://openalex.org/W4392251904","https://openalex.org/W6632323398"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918","https://openalex.org/W4386159726"],"abstract_inverted_index":{"Sound":[0,17,22,234],"Event":[1,18],"Detection":[2,19],"and":[3,21,40,44,54,73,92,95,132,152,201,211,218,259],"Localization":[4,24],"(SELD)":[5],"is":[6,107,264],"a":[7,176],"comprehensive":[8],"task":[9,28],"that":[10],"aims":[11],"to":[12,35,63,74,109,135,162,194,214,248],"solve":[13,36],"the":[14,33,61,70,76,82,99,104,111,124,144,149,155,158,164,169,173,184,195,198,203,208,216,222,231,243,249,255,260],"subtasks":[15],"of":[16,29,47,126,148,168,175,189,197,207,221,245,257],"(SED)":[20],"Source":[23],"(SSL)":[25],"simultaneously.":[26],"The":[27],"SELD":[30,246],"lies":[31],"in":[32,52,183,187],"need":[34],"both":[37],"sound":[38,48,77],"recognition":[39],"spatial":[41],"localization":[42],"problems,":[43],"different":[45,66],"categories":[46],"events":[49,67],"may":[50],"overlap":[51],"time":[53,72,212],"space,":[55],"making":[56],"it":[57],"more":[58],"difficult":[59],"for":[60,119,224],"model":[62,223],"distinguish":[64],"between":[65,157],"occurring":[68],"at":[69],"same":[71],"locate":[75],"source.":[78],"In":[79],"this":[80],"study,":[81],"Dual-conv":[83,114],"Coordinate":[84,93,115,133],"Attention":[85,116,134],"Module":[86],"(DCAM)":[87],"combines":[88],"dual":[89],"convolutional":[90],"blocks":[91],"Attention,":[94],"based":[96,102],"on":[97,103,123,143,230],"this,":[98],"network":[100,186,251],"architecture":[101],"two-stage":[105,185,250],"strategy":[106],"improved":[108],"form":[110],"SELD-oriented":[112],"Two-Stage":[113],"Model":[117],"(TDCAM)":[118],"SELD.":[120],"TDCAM":[121],"draws":[122],"concepts":[125],"Visual":[127],"Geometry":[128],"Group":[129],"(VGG)":[130],"networks":[131],"effectively":[136],"capture":[137],"critical":[138],"local":[139],"information":[140,147],"by":[141,266],"focusing":[142],"coordinate":[145],"space":[146],"feature":[150,159,165],"map":[151,160],"dealing":[153],"with":[154],"relationship":[156],"channels":[161],"enhance":[163],"selection":[166],"capability":[167],"model.":[170,253],"To":[171],"address":[172],"limitation":[174],"single-layer":[177],"Bi-directional":[178],"Gated":[179],"Recurrent":[180],"Unit":[181],"(Bi-GRU)":[182],"terms":[188],"timing":[190,225],"processing,":[191],"we":[192],"add":[193],"structure":[196,263],"two-layer":[199,261],"Bi-GRU":[200,262],"introduce":[202],"data":[204],"enhancement":[205],"techniques":[206],"frequency":[209],"mask":[210,213],"improve":[215],"modeling":[217],"generalization":[219],"ability":[220],"features.":[226],"Through":[227],"experimental":[228],"validation":[229],"TAU":[232],"Spatial":[233],"Events":[235],"2019":[236],"development":[237],"dataset,":[238],"our":[239],"approach":[240],"significantly":[241],"improves":[242],"performance":[244],"compared":[247],"baseline":[252],"Furthermore,":[254],"effectiveness":[256],"DCAM":[258],"confirmed":[265],"performing":[267],"ablation":[268],"experiments.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
