{"id":"https://openalex.org/W4324116353","doi":"https://doi.org/10.1109/taslp.2023.3256088","title":"A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection","display_name":"A Four-Stage Data Augmentation Approach to ResNet-Conformer Based Acoustic Modeling for Sound Event Localization and Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4324116353","doi":"https://doi.org/10.1109/taslp.2023.3256088"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3256088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3256088","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/A5100434900","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3843-3920"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0003-3843-3920","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-2387-0389","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035180322","display_name":"Huaxin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hua-Xin Wu","raw_affiliation_strings":["iFlytek, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101924451","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0002-7073-1744"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFlytek, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079840202","display_name":"Feng Ma","orcid":"https://orcid.org/0009-0004-5289-8075"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Ma","raw_affiliation_strings":["iFlytek, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFlytek, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1892-2551","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.2019,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":{"value":0.99384388,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"1251","last_page":"1264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.994700014591217,"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":0.6837338209152222},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6048161387443542},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5780264735221863},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43805310130119324},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4148162007331848},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3795158267021179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36709877848625183},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11301922798156738},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09419041872024536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6837338209152222},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6048161387443542},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5780264735221863},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43805310130119324},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4148162007331848},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3795158267021179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36709877848625183},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11301922798156738},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09419041872024536},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3256088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3256088","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":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G1713836045","display_name":null,"funder_award_id":"62171427","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1511170870","https://openalex.org/W1970578576","https://openalex.org/W1972567154","https://openalex.org/W1979651826","https://openalex.org/W2023254078","https://openalex.org/W2046317813","https://openalex.org/W2077159900","https://openalex.org/W2103088716","https://openalex.org/W2110412069","https://openalex.org/W2113638573","https://openalex.org/W2114863372","https://openalex.org/W2123843894","https://openalex.org/W2128131274","https://openalex.org/W2130357996","https://openalex.org/W2135131618","https://openalex.org/W2143027228","https://openalex.org/W2156163116","https://openalex.org/W2158143227","https://openalex.org/W2194775991","https://openalex.org/W2204091679","https://openalex.org/W2292996718","https://openalex.org/W2341412280","https://openalex.org/W2400339399","https://openalex.org/W2407005679","https://openalex.org/W2509065397","https://openalex.org/W2531409750","https://openalex.org/W2570915410","https://openalex.org/W2591013610","https://openalex.org/W2745195618","https://openalex.org/W2746554716","https://openalex.org/W2772289775","https://openalex.org/W2775795276","https://openalex.org/W2810934215","https://openalex.org/W2883135409","https://openalex.org/W2888867175","https://openalex.org/W2897282582","https://openalex.org/W2897361856","https://openalex.org/W2936774411","https://openalex.org/W2942551338","https://openalex.org/W2947942791","https://openalex.org/W2962708126","https://openalex.org/W2963158330","https://openalex.org/W2963543871","https://openalex.org/W2964342924","https://openalex.org/W2982382207","https://openalex.org/W2982680886","https://openalex.org/W2998139081","https://openalex.org/W3015931889","https://openalex.org/W3016037102","https://openalex.org/W3021261768","https://openalex.org/W3097777922","https://openalex.org/W3098357269","https://openalex.org/W3098454764","https://openalex.org/W3102937397","https://openalex.org/W3132182240","https://openalex.org/W3135042544","https://openalex.org/W3163842642","https://openalex.org/W3176465185","https://openalex.org/W3212486120","https://openalex.org/W4221167652","https://openalex.org/W4225270933","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6632323398","https://openalex.org/W6677170001","https://openalex.org/W6743446608","https://openalex.org/W6745136726","https://openalex.org/W6747218270","https://openalex.org/W6779923105","https://openalex.org/W6780021897","https://openalex.org/W6796679619","https://openalex.org/W6838853441","https://openalex.org/W6922472746"],"related_works":["https://openalex.org/W3081694532","https://openalex.org/W2092272653","https://openalex.org/W1980230116","https://openalex.org/W4387002515","https://openalex.org/W1517958729","https://openalex.org/W2002555665","https://openalex.org/W271627879","https://openalex.org/W2170155919","https://openalex.org/W2349444258","https://openalex.org/W1985388337"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,24,163],"propose":[4],"a":[5,110,165],"novel":[6],"four-stage":[7,117],"data":[8,42,55,72,99,118,134],"augmentation":[9,28,119,138],"approach":[10,139],"to":[11,39,75,92,113,168],"ResNet-Conformer":[12,166],"based":[13],"acoustic":[14,66,79],"modeling":[15],"for":[16],"sound":[17,96],"event":[18],"localization":[19,76],"and":[20,35,47,85,98,105,125,130,172,180],"detection":[21],"(SELD).":[22],"First,":[23],"explore":[25],"two":[26],"spatial":[27],"techniques,":[29],"namely":[30],"audio":[31,178],"channel":[32],"swapping":[33],"(ACS)":[34],"multi-channel":[36],"simulation":[37],"(MCS),":[38],"deal":[40,93],"with":[41,56,69,94],"sparsity":[43],"in":[44,109,149,153,185],"SELD.":[45],"ACS":[46],"MDS":[48],"focus":[49],"on":[50,122],"augmenting":[51],"the":[52,65,70,123,142,150,154,158,182,186],"limited":[53],"training":[54],"expanding":[57],"direction":[58],"of":[59,78,127,157,176],"arrival":[60],"(DOA)":[61],"representations":[62],"such":[63],"that":[64],"models":[67],"trained":[68],"augmented":[71],"are":[73,89,107],"robust":[74],"variations":[77],"sources.":[80],"Next,":[81],"time-domain":[82],"mixing":[83],"(TDM)":[84],"time-frequency":[86],"masking":[87],"(TFM)":[88],"also":[90],"investigated":[91],"overlapping":[95],"events":[97],"diversity.":[100],"Finally,":[101],"ACS,":[102],"MCS,":[103],"TDM":[104],"TFM":[106],"combined":[108],"step-by-step":[111],"manner":[112],"form":[114],"an":[115,177],"effective":[116],"scheme.":[120],"Tested":[121],"Detection":[124],"Classification":[126],"Acoustic":[128],"Scenes":[129],"Events":[131],"(DCASE)":[132],"2020":[133,160],"set,":[135],"our":[136,146],"proposed":[137],"greatly":[140],"improves":[141],"system":[143,148],"performance,":[144],"ranking":[145],"submitted":[147],"first":[151,183],"place":[152,184],"SELD":[155,189],"task":[156],"DCASE":[159,187],"Challenge.":[161],"Furthermore,":[162],"employ":[164],"architecture":[167],"model":[169],"both":[170],"global":[171],"local":[173],"context":[174],"dependencies":[175],"sequence":[179],"win":[181],"2022":[188],"evaluations.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":36},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}