{"id":"https://openalex.org/W3164302487","doi":"https://doi.org/10.1109/tmm.2022.3178591","title":"Cross-Referencing Self-Training Network for Sound Event Detection in Audio Mixtures","display_name":"Cross-Referencing Self-Training Network for Sound Event Detection in Audio Mixtures","publication_year":2022,"publication_date":"2022-05-27","ids":{"openalex":"https://openalex.org/W3164302487","doi":"https://doi.org/10.1109/tmm.2022.3178591","mag":"3164302487","pmid":"https://pubmed.ncbi.nlm.nih.gov/37928617"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2022.3178591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3178591","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.13392","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100750094","display_name":"Sangwook Park","orcid":"https://orcid.org/0000-0002-6817-4846"},"institutions":[{"id":"https://openalex.org/I133533813","display_name":"Gangneung\u2013Wonju National University","ror":"https://ror.org/0461cvh40","country_code":"KR","type":"education","lineage":["https://openalex.org/I133533813"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangwook Park","raw_affiliation_strings":["Department of Electronic Engineering, Gangneung-Wonju National University, Gangneung, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Gangneung-Wonju National University, Gangneung, South Korea","institution_ids":["https://openalex.org/I133533813"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102000970","display_name":"David K. Han","orcid":"https://orcid.org/0000-0001-5055-5408"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David K. Han","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5055-5408","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038788686","display_name":"Mounya Elhilali","orcid":"https://orcid.org/0000-0003-2597-738X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mounya Elhilali","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA","Department of Psychology and Brain Sciences, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":"https://orcid.org/0000-0003-2597-738X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Psychology and Brain Sciences, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9322,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85261754,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"25","issue":null,"first_page":"4573","last_page":"4585"},"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":0.9983999729156494,"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":0.9900000095367432,"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":0.8533246517181396},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5374823808670044},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5212117433547974},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5204837322235107},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5113880038261414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3581780791282654},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34779298305511475},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3197203278541565},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1803983449935913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8533246517181396},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5374823808670044},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5212117433547974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5204837322235107},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5113880038261414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3581780791282654},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34779298305511475},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3197203278541565},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1803983449935913},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tmm.2022.3178591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2022.3178591","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Transactions on Multimedia","raw_type":"journal-article"},{"id":"pmid:37928617","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37928617","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on multimedia","raw_type":null},{"id":"pmh:oai:arXiv.org:2105.13392","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.13392","pdf_url":"https://arxiv.org/pdf/2105.13392","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:10621403","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10621403","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10621403/pdf/nihms-1939254.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Multimedia","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.13392","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.13392","pdf_url":"https://arxiv.org/pdf/2105.13392","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1163831516","display_name":null,"funder_award_id":"1734744","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G116800654","display_name":null,"funder_award_id":"1734744","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G1190045714","display_name":null,"funder_award_id":"N00014-17-1-2736","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G1268790335","display_name":null,"funder_award_id":"N00014-17-1-2736","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2392191984","display_name":null,"funder_award_id":"U01AG058532","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G2859612778","display_name":null,"funder_award_id":"N00014-19-1-2689","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3133924050","display_name":null,"funder_award_id":"N00014-19-1-2689","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4279338039","display_name":null,"funder_award_id":"1734744","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4504108201","display_name":null,"funder_award_id":"N00014-17-1","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4724799603","display_name":null,"funder_award_id":"N00014-19-1-2689","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5365771482","display_name":null,"funder_award_id":"U01AG058532","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5510659804","display_name":null,"funder_award_id":"U01AG058532","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7389886942","display_name":null,"funder_award_id":"N00014-17-1-2736","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G82448446","display_name":"NCS-FO: Active Listening and Attention in 3D Natural Scenes","funder_award_id":"1734744","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"},{"id":"https://openalex.org/F4320337337","display_name":"National Institute on Aging","ror":"https://ror.org/049v75w11"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W92894758","https://openalex.org/W1654482605","https://openalex.org/W2024991751","https://openalex.org/W2030476695","https://openalex.org/W2033875152","https://openalex.org/W2079057609","https://openalex.org/W2138776269","https://openalex.org/W2138857742","https://openalex.org/W2145494108","https://openalex.org/W2152842394","https://openalex.org/W2153579005","https://openalex.org/W2170021787","https://openalex.org/W2219249508","https://openalex.org/W2293363371","https://openalex.org/W2331825095","https://openalex.org/W2408239454","https://openalex.org/W2431080869","https://openalex.org/W2513863019","https://openalex.org/W2530816535","https://openalex.org/W2591013610","https://openalex.org/W2592691248","https://openalex.org/W2597218230","https://openalex.org/W2606321545","https://openalex.org/W2612678766","https://openalex.org/W2695712842","https://openalex.org/W2719034351","https://openalex.org/W2765407302","https://openalex.org/W2810417023","https://openalex.org/W2897282582","https://openalex.org/W2921087533","https://openalex.org/W2936503027","https://openalex.org/W2938357656","https://openalex.org/W2950746339","https://openalex.org/W2951970475","https://openalex.org/W2953070460","https://openalex.org/W2959539607","https://openalex.org/W2963216549","https://openalex.org/W2963399829","https://openalex.org/W2963956526","https://openalex.org/W2984353870","https://openalex.org/W3015805515","https://openalex.org/W3036237438","https://openalex.org/W3039083022","https://openalex.org/W3049446265","https://openalex.org/W3094760673","https://openalex.org/W3097777922","https://openalex.org/W3109837239","https://openalex.org/W3119841144","https://openalex.org/W3120044914","https://openalex.org/W3121328487","https://openalex.org/W3136198447","https://openalex.org/W3160339728","https://openalex.org/W3161272933","https://openalex.org/W3209458476","https://openalex.org/W4249009152","https://openalex.org/W4294170691","https://openalex.org/W4384306313","https://openalex.org/W6603760306","https://openalex.org/W6680300913","https://openalex.org/W6681588610","https://openalex.org/W6682691769","https://openalex.org/W6688816777","https://openalex.org/W6717772578","https://openalex.org/W6733814495","https://openalex.org/W6745136726","https://openalex.org/W6764051988","https://openalex.org/W6779574021","https://openalex.org/W6780411803","https://openalex.org/W6784232266","https://openalex.org/W6784400889","https://openalex.org/W6791883635"],"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/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2157165686","https://openalex.org/W2371215329","https://openalex.org/W1975359510"],"abstract_inverted_index":{"Sound":[0],"event":[1,29,50,138,148],"detection":[2,51,139,149],"is":[3,144],"an":[4,97],"important":[5],"facet":[6],"of":[7,15,48,57,77,88,94,157,167],"audio":[8],"tagging":[9],"that":[10,73,116],"aims":[11],"to":[12,85,174],"identify":[13],"sounds":[14],"interest":[16],"and":[17,23,61,80,91,119,163],"define":[18],"both":[19,161],"the":[20,46,55,99,152,175],"sound":[21,28,49,89,128,137,147],"category":[22,90],"time":[24,92],"boundaries":[25],"for":[26,106,133,151],"each":[27],"in":[30,36,45,83,136,179],"a":[31,103,113],"continuous":[32],"recording.":[33],"With":[34],"advances":[35],"deep":[37],"neural":[38],"networks,":[39],"there":[40],"has":[41],"been":[42],"tremendous":[43],"improvement":[44,135,172],"performance":[47],"systems,":[52],"although":[53],"at":[54],"expense":[56],"costly":[58],"data":[59,78,111],"collection":[60],"labeling":[62],"efforts.":[63],"In":[64],"fact,":[65],"current":[66,100],"state-of-the-art":[67],"methods":[68,72,159],"employ":[69],"supervised":[70],"training":[71],"leverage":[74],"large":[75],"amounts":[76],"samples":[79],"corresponding":[81],"labels":[82],"order":[84],"facilitate":[86],"identification":[87],"stamps":[93],"events.":[95],"As":[96],"alternative,":[98],"study":[101],"proposes":[102],"semi-supervised":[104,180],"method":[105],"generating":[107],"pseudo-labels":[108],"from":[109,130],"unsupervised":[110],"using":[112],"student-teacher":[114],"scheme":[115],"balances":[117],"self-training":[118],"cross-training.":[120],"Additionally,":[121],"this":[122],"paper":[123],"explores":[124],"post-processing":[125],"which":[126],"extracts":[127],"intervals":[129],"network":[131],"prediction,":[132],"further":[134],"performance.":[140],"The":[141,155],"proposed":[142],"approach":[143],"evaluated":[145],"on":[146,160],"task":[150],"DCASE2020":[153],"challenge.":[154],"results":[156],"these":[158],"\"validation\"":[162],"\"public":[164],"evaluation\"":[165],"sets":[166],"DESED":[168],"database":[169],"show":[170],"significant":[171],"compared":[173],"state-of-the":[176],"art":[177],"systems":[178],"learning.":[181]},"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":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-23T13:55:30.953635","created_date":"2025-10-10T00:00:00"}