{"id":"https://openalex.org/W4403183273","doi":"https://doi.org/10.1109/lsp.2024.3475350","title":"Automated Audio Data Augmentation Network Using Bi-Level Optimization for Sound Event Localization and Detection","display_name":"Automated Audio Data Augmentation Network Using Bi-Level Optimization for Sound Event Localization and Detection","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403183273","doi":"https://doi.org/10.1109/lsp.2024.3475350"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3475350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3475350","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5044368396","display_name":"Wenjie Zhang","orcid":"https://orcid.org/0000-0002-8527-9826"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenjie Zhang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110703803","display_name":"Peng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Yu","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101051257","display_name":"Jun Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yin","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060665015","display_name":"Xiaoheng Jiang","orcid":"https://orcid.org/0000-0002-5770-0417"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoheng Jiang","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081346568","display_name":"Mingliang Xu","orcid":"https://orcid.org/0000-0002-6885-3451"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingliang Xu","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5044368396"],"corresponding_institution_ids":["https://openalex.org/I38877650"],"apc_list":null,"apc_paid":null,"fwci":0.7471,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70632329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"31","issue":null,"first_page":"2770","last_page":"2774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9876000285148621,"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":0.9876000285148621,"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":0.982200026512146,"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":0.9226999878883362,"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":0.7132933139801025},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5762923359870911},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5636486411094666},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49030378460884094},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.41176721453666687},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.40924063324928284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3638022840023041},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.33189770579338074},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.23680534958839417},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1904696524143219}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132933139801025},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5762923359870911},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5636486411094666},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49030378460884094},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.41176721453666687},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.40924063324928284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3638022840023041},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33189770579338074},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.23680534958839417},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1904696524143219},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3475350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3475350","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5570243985","display_name":null,"funder_award_id":"232300421093","funder_id":"https://openalex.org/F4320323845","funder_display_name":"Natural Science Foundation of Henan Province"},{"id":"https://openalex.org/G7272499820","display_name":null,"funder_award_id":"U21B2037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7360235455","display_name":null,"funder_award_id":"62003308","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8306412014","display_name":null,"funder_award_id":"62172371","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"},{"id":"https://openalex.org/F4320323845","display_name":"Natural Science Foundation of Henan Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2942551338","https://openalex.org/W2949736877","https://openalex.org/W2982680886","https://openalex.org/W3009184501","https://openalex.org/W3034302278","https://openalex.org/W3119329762","https://openalex.org/W3123350987","https://openalex.org/W3131833214","https://openalex.org/W3163193264","https://openalex.org/W3163881933","https://openalex.org/W3176115897","https://openalex.org/W3203177955","https://openalex.org/W3205267198","https://openalex.org/W4213362076","https://openalex.org/W4220808775","https://openalex.org/W4221141618","https://openalex.org/W4286507093","https://openalex.org/W4312439170","https://openalex.org/W4324116353","https://openalex.org/W4372263497","https://openalex.org/W4385164055","https://openalex.org/W4390873785","https://openalex.org/W4394860798","https://openalex.org/W4394862890","https://openalex.org/W6762619590","https://openalex.org/W6838853441","https://openalex.org/W6853532597","https://openalex.org/W6998305694"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W3004352674","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2098934641","https://openalex.org/W2157165686"],"abstract_inverted_index":{"In":[0,91],"sound":[1],"event":[2],"localization":[3,11],"and":[4,12],"detection":[5,13],"(SELD),":[6],"traditional":[7,161],"methods":[8],"often":[9],"treat":[10],"algorithms":[14],"separately":[15],"from":[16,125],"data":[17,27,38,48,85,106,111,162],"augmentation.":[18],"During":[19],"the":[20,24,69,92,95,104,119,126,141,156],"model":[21],"training":[22],"process,":[23],"strategy":[25,77],"for":[26,47,103,133,165],"augmentation":[28,39,49,86,107,112,163],"is":[29],"typically":[30],"implemented":[31],"in":[32],"a":[33,101,149],"non-learnable":[34],"manner.":[35],"Existing":[36],"audio":[37,84,110],"strategies":[40,164],"struggle":[41],"to":[42,55,81],"find":[43],"optimal":[44,131],"parameter":[45],"solutions":[46],"that":[50],"can":[51],"be":[52],"effectively":[53],"applied":[54],"SELD":[56,89,97,127,150],"systems.":[57],"To":[58],"address":[59],"this":[60],"challenge,":[61],"we":[62],"introduce":[63],"an":[64],"innovative":[65],"network-based":[66],"strategy,":[67],"termed":[68],"Automated":[70],"Audio":[71],"Data":[72],"Augmentation":[73],"(AADA)":[74],"network.":[75],"This":[76],"employs":[78],"bi-level":[79],"optimization":[80],"synergistically":[82],"integrate":[83],"techniques":[87],"with":[88],"tasks.":[90,135],"AADA":[93],"network,":[94],"lower-level":[96],"task":[98],"serves":[99],"as":[100],"constraint":[102],"higher-level":[105],"process.":[108],"The":[109],"parameters":[113,132],"are":[114],"adaptively":[115],"optimized":[116],"by":[117],"utilizing":[118],"transfer":[120],"of":[121,137,152,159],"intermediate":[122],"feature":[123],"information":[124],"tasks,":[128],"thus":[129],"obtaining":[130],"these":[134],"Evaluation":[136],"our":[138],"approach":[139],"on":[140],"Sony-TAU":[142],"Realistic":[143],"Spatial":[144],"Soundscapes":[145],"2023":[146],"dataset":[147],"achieves":[148],"score":[151],"0.4801,":[153],"significantly":[154],"surpassing":[155],"performance":[157],"metrics":[158],"all":[160],"SELD.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
