{"id":"https://openalex.org/W4402677768","doi":"https://doi.org/10.3390/s24186090","title":"Joint Spatio-Temporal-Frequency Representation Learning for Improved Sound Event Localization and Detection","display_name":"Joint Spatio-Temporal-Frequency Representation Learning for Improved Sound Event Localization and Detection","publication_year":2024,"publication_date":"2024-09-20","ids":{"openalex":"https://openalex.org/W4402677768","doi":"https://doi.org/10.3390/s24186090","pmid":"https://pubmed.ncbi.nlm.nih.gov/39338835"},"language":"en","primary_location":{"id":"doi:10.3390/s24186090","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24186090","pdf_url":null,"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://doi.org/10.3390/s24186090","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058314453","display_name":"Baoqing Chen","orcid":"https://orcid.org/0000-0001-9807-7425"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baoqing Chen","raw_affiliation_strings":["School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052103784","display_name":"M. Wang","orcid":"https://orcid.org/0009-0004-4974-6329"},"institutions":[{"id":"https://openalex.org/I38706770","display_name":"Guilin University of Technology","ror":"https://ror.org/03z391397","country_code":"CN","type":"education","lineage":["https://openalex.org/I38706770"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Wang","raw_affiliation_strings":["College of Physics and Electronic Information Engineering, Guilin University of Technology, Guilin 541004, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Electronic Information Engineering, Guilin University of Technology, Guilin 541004, China","institution_ids":["https://openalex.org/I38706770"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yu Gu","orcid":"https://orcid.org/0009-0007-9009-5099"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Gu","raw_affiliation_strings":["School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication, Guilin University of Electronic Technology, Guilin 541004, China","institution_ids":["https://openalex.org/I5343935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5058314453"],"corresponding_institution_ids":["https://openalex.org/I5343935"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":1.0158,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76047682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"24","issue":"18","first_page":"6090","last_page":"6090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9864000082015991,"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":0.7648752927780151},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6273277997970581},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.49845361709594727},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.471227765083313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4675195515155792},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4329610764980316},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4316192865371704},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43041807413101196},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4027118682861328},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39929983019828796},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08889174461364746},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08779224753379822},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.08397623896598816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648752927780151},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6273277997970581},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.49845361709594727},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.471227765083313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4675195515155792},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4329610764980316},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4316192865371704},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43041807413101196},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4027118682861328},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39929983019828796},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08889174461364746},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08779224753379822},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.08397623896598816},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/s24186090","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24186090","pdf_url":null,"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:39338835","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39338835","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:11436190","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11436190","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11436190/pdf/sensors-24-06090.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"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:3e1abded2ca04ea6b533c4eb7f422603","is_oa":true,"landing_page_url":"https://doaj.org/article/3e1abded2ca04ea6b533c4eb7f422603","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":"Sensors, Vol 24, Iss 18, p 6090 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/s24186090","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s24186090","pdf_url":null,"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":[{"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/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/G37568934","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5220032274","display_name":null,"funder_award_id":"62071135","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1924770834","https://openalex.org/W1983364832","https://openalex.org/W2085156437","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2292996718","https://openalex.org/W2752782242","https://openalex.org/W2810934215","https://openalex.org/W2883595988","https://openalex.org/W2884585870","https://openalex.org/W2936774411","https://openalex.org/W2940092410","https://openalex.org/W2942551338","https://openalex.org/W2963495494","https://openalex.org/W2982680886","https://openalex.org/W2998139081","https://openalex.org/W3083274258","https://openalex.org/W3091667472","https://openalex.org/W3098454764","https://openalex.org/W3117314925","https://openalex.org/W3117876421","https://openalex.org/W3163193264","https://openalex.org/W3163881933","https://openalex.org/W3166716987","https://openalex.org/W3167721750","https://openalex.org/W3171659463","https://openalex.org/W3176079376","https://openalex.org/W3177052299","https://openalex.org/W3178592608","https://openalex.org/W3197097128","https://openalex.org/W3197827948","https://openalex.org/W3203177955","https://openalex.org/W3212386989","https://openalex.org/W3213455868","https://openalex.org/W4221141618","https://openalex.org/W4224918663","https://openalex.org/W4225270933","https://openalex.org/W4281742236","https://openalex.org/W4282031641","https://openalex.org/W4285211963","https://openalex.org/W4293092459","https://openalex.org/W4297794384","https://openalex.org/W4324116353","https://openalex.org/W4380032323","https://openalex.org/W4385164055","https://openalex.org/W6631190155","https://openalex.org/W6743440100"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218"],"abstract_inverted_index":{"Sound":[0],"event":[1],"localization":[2],"and":[3,18,35,77,114,142,178],"detection":[4],"(SELD)":[5],"is":[6,125],"a":[7,93,136],"crucial":[8],"component":[9],"of":[10,32,63,69,117,122],"machine":[11],"listening":[12],"that":[13,97,182],"aims":[14],"to":[15,38,47,82,106,140,157],"simultaneously":[16],"identify":[17],"localize":[19],"sound":[20,41,64,118,163],"events":[21],"in":[22,85],"multichannel":[23,54],"audio":[24],"recordings.":[25],"This":[26],"task":[27],"demands":[28],"an":[29],"integrated":[30],"analysis":[31],"spatial,":[33,112],"temporal,":[34,113],"frequency":[36,115],"domains":[37,116],"accurately":[39],"characterize":[40],"events.":[42,119,164],"The":[43,120],"spatial":[44],"domain":[45],"pertains":[46],"the":[48,61,67,99,126,144,154,166,183],"varying":[49],"acoustic":[50],"signals":[51],"captured":[52],"by":[53],"microphones,":[55],"which":[56,131],"are":[57],"essential":[58],"for":[59],"determining":[60],"location":[62],"sources.":[65],"However,":[66],"majority":[68],"recent":[70],"studies":[71],"have":[72],"focused":[73],"on":[74,172],"time-frequency":[75],"correlations":[76,79,146],"spatio-temporal":[78],"separately,":[80],"leading":[81],"inadequate":[83],"performance":[84],"real-life":[86],"scenarios.":[87],"In":[88],"this":[89],"paper,":[90],"we":[91,168],"propose":[92],"novel":[94],"SELD":[95,185],"method":[96,152,186],"utilizes":[98],"newly":[100],"developed":[101],"Spatio-Temporal-Frequency":[102],"Fusion":[103],"Network":[104],"(STFF-Net)":[105],"jointly":[107],"learn":[108],"comprehensive":[109],"features":[110],"across":[111],"backbone":[121],"our":[123,151,179],"STFF-Net":[124],"Enhanced-3D":[127],"(E3D)":[128],"residual":[129],"block,":[130],"combines":[132],"3D":[133],"convolutions":[134],"with":[135],"parameter-free":[137],"attention":[138],"mechanism":[139],"capture":[141],"refine":[143],"intricate":[145],"among":[147],"these":[148],"domains.":[149],"Furthermore,":[150],"incorporates":[153],"multi-ACCDOA":[155],"format":[156],"effectively":[158],"handle":[159],"homogeneous":[160],"overlaps":[161],"between":[162],"During":[165],"evaluation,":[167],"conduct":[169],"extensive":[170],"experiments":[171],"three":[173],"de":[174],"facto":[175],"benchmark":[176],"datasets,":[177],"results":[180],"demonstrate":[181],"proposed":[184],"significantly":[187],"outperforms":[188],"current":[189],"state-of-the-art":[190],"approaches.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}