{"id":"https://openalex.org/W4224918663","doi":"https://doi.org/10.1109/icassp43922.2022.9746673","title":"ICASSP 2022 L3DAS22 Challenge: Ensemble of Resnet-Conformers with Ambisonics Data Augmentation for Sound Event Localization and Detection","display_name":"ICASSP 2022 L3DAS22 Challenge: Ensemble of Resnet-Conformers with Ambisonics Data Augmentation for Sound Event Localization and Detection","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224918663","doi":"https://doi.org/10.1109/icassp43922.2022.9746673"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746673","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5006037669","display_name":"Yongjian Mao","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjian Mao","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,School of Communication and Information Engineering,Chongqing,China","School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,School of Communication and Information Engineering,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101200256","display_name":"Ying Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Zeng","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,School of Communication and Information Engineering,Chongqing,China","School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,School of Communication and Information Engineering,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102001094","display_name":"Hongqing Liu","orcid":"https://orcid.org/0000-0002-2069-0390"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongqing Liu","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,School of Communication and Information Engineering,Chongqing,China","School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,School of Communication and Information Engineering,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025678265","display_name":"Wenbin Zhu","orcid":"https://orcid.org/0000-0001-9158-335X"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin Zhu","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,School of Communication and Information Engineering,Chongqing,China","School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,School of Communication and Information Engineering,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005083930","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0001-7445-226X"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhou","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications,School of Communication and Information Engineering,Chongqing,China","School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications,School of Communication and Information Engineering,Chongqing,China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I10535382"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9191","last_page":"9195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ambisonics","display_name":"Ambisonics","score":0.9075120687484741},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8353467583656311},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.706045925617218},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5305742621421814},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.45783236622810364},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.4543170630931854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45366886258125305},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4343678057193756},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4242820143699646},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.253318727016449},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15504086017608643},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.1534270942211151},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09772533178329468}],"concepts":[{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.9075120687484741},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8353467583656311},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.706045925617218},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5305742621421814},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.45783236622810364},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.4543170630931854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45366886258125305},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4343678057193756},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4242820143699646},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.253318727016449},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15504086017608643},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.1534270942211151},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09772533178329468},{"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/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746673","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1511723925","https://openalex.org/W2034424181","https://openalex.org/W2113638573","https://openalex.org/W2128131274","https://openalex.org/W2130357996","https://openalex.org/W2135131618","https://openalex.org/W2331166300","https://openalex.org/W2793357660","https://openalex.org/W2810934215","https://openalex.org/W2888842465","https://openalex.org/W2917254586","https://openalex.org/W2964342924","https://openalex.org/W3083274258","https://openalex.org/W3094509890","https://openalex.org/W3097777922","https://openalex.org/W3117314925","https://openalex.org/W3120252178","https://openalex.org/W3129370657","https://openalex.org/W3196616101","https://openalex.org/W4225270933","https://openalex.org/W6630773358","https://openalex.org/W6702387769","https://openalex.org/W6788349323"],"related_works":["https://openalex.org/W2120540196","https://openalex.org/W3095343173","https://openalex.org/W2381036744","https://openalex.org/W2288135719","https://openalex.org/W2323749021","https://openalex.org/W2533590149","https://openalex.org/W2901989338","https://openalex.org/W200102888","https://openalex.org/W82005754","https://openalex.org/W2334448276"],"abstract_inverted_index":{"It":[0],"remains":[1],"a":[2,38],"tough":[3],"challenge":[4],"to":[5,112,153,161],"tackle":[6],"sound":[7,16],"event":[8],"localization":[9],"and":[10,20,40,45,50,54,67,85,125,143],"detection":[11],"(SELD)":[12],"problem,":[13],"especially":[14],"when":[15],"scene":[17],"complexity":[18],"increases":[19],"overlapping":[21],"acoustic":[22,69],"sources":[23],"appear.":[24],"To":[25,100],"improve":[26],"the":[27,86,102,131,141,145,149,154],"SELD":[28],"performance,":[29],"we":[30,56,93,107,157],"propose":[31],"an":[32,78],"ensemble":[33],"system,":[34],"which":[35],"consists":[36],"of":[37,104],"ResNet":[39],"Conformer":[41],"backbone":[42],"network":[43],"(SELD-RCnet)":[44],"its":[46],"two":[47,109],"variants,":[48],"SED-RCnet":[49],"SSL-RCnet.":[51],"For":[52,76,91],"SELD-RCnet":[53],"SSL-RCnet,":[55,77],"use":[57,94],"short":[58],"time":[59],"Fourier":[60],"transform":[61],"(STFT)":[62],"magnitude":[63],"spectrogram,":[64,66],"phase":[65],"active":[68],"intensity":[70],"vectors":[71],"(IVs)":[72],"as":[73,97],"input":[74,98],"features.":[75,99],"innovative":[79],"predictive":[80],"target":[81],"is":[82,88],"also":[83],"developed":[84],"performance":[87],"thus":[89],"improved.":[90],"SED-RCnet,":[92],"Log-Mel":[95],"spectrogram":[96],"overcome":[101],"lack":[103],"training":[105],"data,":[106],"adopt":[108],"novel":[110],"approaches":[111],"first":[113],"order":[114],"Ambisonic":[115],"(FOA)":[116],"format":[117],"dataset":[118],"augmentation,":[119],"namely":[120],"audio":[121],"channel":[122],"swapping":[123],"(ACS)":[124],"time-frequency":[126],"masking":[127],"(TFM).":[128],"Finally,":[129],"in":[130,165],"L3DAS22":[132],"Challenge,":[133],"our":[134,163],"submitted":[135],"system":[136,164],"achieves":[137],"significant":[138],"improvements":[139],"over":[140],"baseline":[142],"ranks":[144],"second":[146],"place":[147],"for":[148],"Task2.":[150],"Therefore,":[151],"according":[152],"competition":[155],"rules,":[156],"submit":[158],"this":[159],"work":[160],"describe":[162],"details.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}