{"id":"https://openalex.org/W4380032323","doi":"https://doi.org/10.1109/taslp.2023.3284525","title":"Sound Events Localization and Detection Using Bio-Inspired Gammatone Filters and Temporal Convolutional Neural Networks","display_name":"Sound Events Localization and Detection Using Bio-Inspired Gammatone Filters and Temporal Convolutional Neural Networks","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4380032323","doi":"https://doi.org/10.1109/taslp.2023.3284525"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3284525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3284525","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","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":"https://openalex.org/A5002311406","display_name":"Karen Rosero","orcid":"https://orcid.org/0000-0002-8118-4213"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Karen Gissell Rosero Jacome","raw_affiliation_strings":["School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-8118-4213","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018868577","display_name":"Felipe Grijalva","orcid":"https://orcid.org/0000-0001-6162-3429"},"institutions":[{"id":"https://openalex.org/I69094615","display_name":"Universidad San Francisco de Quito","ror":"https://ror.org/01r2c3v86","country_code":"EC","type":"education","lineage":["https://openalex.org/I69094615"]}],"countries":["EC"],"is_corresponding":false,"raw_author_name":"Felipe Leonel Grijalva","raw_affiliation_strings":["Colegio de Ciencias e Ingenierías “El Politécnico”, Universidad San Francisco de Quito, Quito, Ecuador"],"raw_orcid":"https://orcid.org/0000-0001-6162-3429","affiliations":[{"raw_affiliation_string":"Colegio de Ciencias e Ingenierías “El Politécnico”, Universidad San Francisco de Quito, Quito, Ecuador","institution_ids":["https://openalex.org/I69094615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030262162","display_name":"Bruno Masiero","orcid":"https://orcid.org/0000-0002-2246-4450"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Bruno Sanches Masiero","raw_affiliation_strings":["School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-2246-4450","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil","institution_ids":["https://openalex.org/I181391015"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5002311406"],"corresponding_institution_ids":["https://openalex.org/I181391015"],"apc_list":null,"apc_paid":null,"fwci":4.4135,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95636026,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"2314","last_page":"2324"},"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7867904901504517},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6569491624832153},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6114786863327026},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6087507605552673},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5070104598999023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4942615032196045},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.48867228627204895},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4876760244369507},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4264778792858124},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4258362948894501},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35507357120513916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867904901504517},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6569491624832153},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6114786863327026},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6087507605552673},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5070104598999023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4942615032196045},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.48867228627204895},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4876760244369507},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4264778792858124},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4258362948894501},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35507357120513916},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3284525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3284525","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5145566128","display_name":null,"funder_award_id":"2019/22945-3","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G7141543451","display_name":null,"funder_award_id":"2017/08120-6","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320326549","display_name":"Universidad San Francisco de Quito","ror":"https://ror.org/01r2c3v86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W84900616","https://openalex.org/W132822091","https://openalex.org/W1422086691","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1553812195","https://openalex.org/W1555217905","https://openalex.org/W1579233002","https://openalex.org/W1994379197","https://openalex.org/W2038484192","https://openalex.org/W2060741034","https://openalex.org/W2078976049","https://openalex.org/W2106583743","https://openalex.org/W2113744809","https://openalex.org/W2117176618","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2397728357","https://openalex.org/W2608422710","https://openalex.org/W2775794021","https://openalex.org/W2781749069","https://openalex.org/W2792764867","https://openalex.org/W2796130257","https://openalex.org/W2810934215","https://openalex.org/W2936774411","https://openalex.org/W2964342924","https://openalex.org/W2979503749","https://openalex.org/W2998139081","https://openalex.org/W3009685637","https://openalex.org/W3037468418","https://openalex.org/W3163193264","https://openalex.org/W3176079376","https://openalex.org/W3177143793","https://openalex.org/W3180479040","https://openalex.org/W3201472659","https://openalex.org/W3212486120","https://openalex.org/W4205689591","https://openalex.org/W4241068368","https://openalex.org/W4287120192","https://openalex.org/W4287751091","https://openalex.org/W4394669361","https://openalex.org/W6628353819","https://openalex.org/W6631190155","https://openalex.org/W6634517665","https://openalex.org/W6677667490","https://openalex.org/W6749825310","https://openalex.org/W6760529994","https://openalex.org/W6796679619","https://openalex.org/W6797253786","https://openalex.org/W6797669297","https://openalex.org/W6798291457"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W3008584592","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3029198973"],"abstract_inverted_index":{"The":[0,23,149],"auditory":[1,100],"brain":[2],"circuits":[3],"are":[4,136],"biologically":[5],"constructed":[6],"to":[7,88,127,138,182],"recognize":[8],"and":[9,61,102,159,179],"localize":[10],"sounds":[11],"by":[12,29,96],"encoding":[13],"a":[14,54,117,124],"combination":[15],"of":[16,25,74,92,116,143,176],"cues":[17],"that":[18,46],"help":[19],"individuals":[20],"interpret":[21],"sounds.":[22],"development":[24],"computational":[26],"methods":[27],"inspired":[28],"human":[30],"capacities":[31],"has":[32],"established":[33],"opportunities":[34],"for":[35,57,106],"improving":[36],"machine":[37],"hearing.":[38],"Recent":[39],"studies":[40],"based":[41],"on":[42,68,168],"deep":[43],"learning":[44],"show":[45],"using":[47,97],"convolutional":[48,119],"recurrent":[49],"neural":[50],"networks":[51],"(CRNNs)":[52],"is":[53,77],"promising":[55],"approach":[56],"sound":[58,70,184],"event":[59],"detection":[60],"localization":[62],"in":[63,145,187],"spatial":[64,146,170],"sound.":[65],"Nevertheless,":[66],"depending":[67],"the":[69,72,90,107,114,140,165],"environment,":[71],"performance":[73,91],"these":[75],"systems":[76,95],"still":[78],"far":[79],"from":[80],"reaching":[81],"perfect":[82],"metrics.":[83],"Therefore,":[84],"this":[85],"work":[86],"intends":[87],"boost":[89],"state-of-the-art":[93],"(SOTA)":[94],"bio-inspired":[98],"gammatone":[99],"filters":[101],"intensity":[103],"vectors":[104],"(IVs)":[105],"acoustic":[108],"feature":[109],"extraction":[110],"stage,":[111],"along":[112],"with":[113,173,180],"implementation":[115],"temporal":[118],"network":[120],"(TCN)":[121],"block":[122],"into":[123],"CRNN":[125],"model,":[126],"capture":[128],"long":[129],"term":[130],"dependencies.":[131],"Three":[132],"data":[133],"augmentation":[134],"techniques":[135],"applied":[137],"increase":[139],"small":[141],"number":[142],"samples":[144],"audio":[147,171],"datasets.":[148],"mentioned":[150],"stages":[151],"constitute":[152],"our":[153],"proposed":[154],"Gammatone-based":[155],"Sound":[156],"Events":[157],"Localization":[158],"Detection":[160],"(G-SELD)":[161],"system,":[162],"which":[163],"exceeded":[164],"SOTA":[166],"results":[167],"four":[169],"datasets":[172],"different":[174],"levels":[175],"acoustical":[177],"complexity":[178],"up":[181],"three":[183],"sources":[185],"overlapping":[186],"time.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}