{"id":"https://openalex.org/W4372259938","doi":"https://doi.org/10.1109/icassp49357.2023.10095011","title":"The NERCSLIP-USTC System for the L3DAS23 Challenge Task2: 3D Sound Event Localization and Detection (SELD)","display_name":"The NERCSLIP-USTC System for the L3DAS23 Challenge Task2: 3D Sound Event Localization and Detection (SELD)","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259938","doi":"https://doi.org/10.1109/icassp49357.2023.10095011"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5036925221","display_name":"Haoyin Yan","orcid":null},"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":true,"raw_author_name":"Haoyin Yan","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","NERC-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008599015","display_name":"Haitao Xu","orcid":"https://orcid.org/0000-0001-9242-262X"},"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":"Haitao Xu","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","NERC-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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 (USTC),NERC-SLIP,Hefei,China","NERC-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100436848","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0003-1124-0854"},"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":"Jie Zhang","raw_affiliation_strings":["University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","NERC-SLIP, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"NERC-SLIP, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036925221"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.8133,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69925518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"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":0.9993000030517578,"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":0.9951000213623047,"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":0.6270724534988403},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6024898886680603},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.46691420674324036},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41197073459625244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3365320563316345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3263263702392578},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1584404706954956},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1310884654521942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6270724534988403},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6024898886680603},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.46691420674324036},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41197073459625244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3365320563316345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3263263702392578},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1584404706954956},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1310884654521942},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2765407302","https://openalex.org/W2810934215","https://openalex.org/W2936774411","https://openalex.org/W2998139081","https://openalex.org/W3091667472","https://openalex.org/W3097777922","https://openalex.org/W3120252178","https://openalex.org/W4225270933","https://openalex.org/W6687483927","https://openalex.org/W6745136726","https://openalex.org/W6784117923","https://openalex.org/W6788349323"],"related_works":["https://openalex.org/W2588198209","https://openalex.org/W1909006023","https://openalex.org/W4205824991","https://openalex.org/W3200723557","https://openalex.org/W4312713546","https://openalex.org/W2362195430","https://openalex.org/W2347494122","https://openalex.org/W2567983276","https://openalex.org/W2802298219","https://openalex.org/W2393996461"],"abstract_inverted_index":{"Sound":[0],"event":[1,18],"localization":[2],"and":[3,20,53,62,75,95],"detection":[4],"(SELD)":[5],"aims":[6],"at":[7],"identifying":[8],"the":[9,67,89,92,97,104],"temporal":[10],"activities":[11],"of":[12,16,91],"a":[13,37],"known":[14],"set":[15],"sound":[17],"classes":[19],"estimating":[21],"their":[22],"locations.":[23],"It":[24],"remains":[25],"challenging":[26],"especially":[27],"when":[28],"there":[29],"are":[30,56,81],"overlapped":[31],"acoustic":[32],"events.":[33],"In":[34],"this":[35],"work,":[36],"robust":[38],"network":[39],"architecture":[40],"with":[41],"data":[42,68],"augmentation":[43],"techniques":[44,80],"is":[45,86],"proposed":[46,84],"to":[47,58],"improve":[48],"SELD":[49],"performance,":[50],"where":[51],"ResNet":[52],"Conformer":[54],"blocks":[55],"combined":[57],"model":[59],"both":[60],"local":[61],"global":[63],"patterns.":[64],"To":[65],"address":[66],"sparsity":[69],"issue":[70],"in":[71,88],"SELD,":[72],"SpecAugment,":[73],"mixup":[74],"audio":[76],"channel":[77],"swapping":[78],"(ACS)":[79],"adopted.":[82],"Our":[83],"system":[85],"evaluated":[87],"Task2":[90],"L3DAS23":[93],"challenge":[94],"ranks":[96],"second":[98],"place,":[99],"achieving":[100],"significant":[101],"improvements":[102],"over":[103],"baseline.":[105]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
