{"id":"https://openalex.org/W3042805811","doi":"https://doi.org/10.1109/taslp.2020.3008832","title":"Audio Tagging by Cross Filtering Noisy Labels","display_name":"Audio Tagging by Cross Filtering Noisy Labels","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3042805811","doi":"https://doi.org/10.1109/taslp.2020.3008832","mag":"3042805811"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2020.3008832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3008832","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.08165","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Boqing Zhu","orcid":"https://orcid.org/0000-0001-7867-2112"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Boqing Zhu","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huaimin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaimin Wang","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yuxing Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxing Peng","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Laboratory, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":1.6736,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.84597342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"28","issue":null,"first_page":"2073","last_page":"2083"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.5526000261306763,"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":0.5526000261306763,"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":0.15060000121593475,"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":0.11999999731779099,"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/function","display_name":"Function (biology)","score":0.5382000207901001},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.5238999724388123},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.5059999823570251},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5041000247001648},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4846000075340271},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4611999988555908},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4390999972820282},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406000137329102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.669700026512146},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.5238999724388123},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.5059999823570251},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4611999988555908},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4147000014781952},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.39899998903274536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.36469998955726624},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2988416141","wikidata":"https://www.wikidata.org/wiki/Q6031139","display_name":"Information loss","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2020.3008832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2020.3008832","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"},{"id":"pmh:oai:arXiv.org:2007.08165","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.08165","pdf_url":"https://arxiv.org/pdf/2007.08165","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.08165","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.08165","pdf_url":"https://arxiv.org/pdf/2007.08165","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":[],"awards":[{"id":"https://openalex.org/G8617305348","display_name":null,"funder_award_id":"81973244","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":42,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W2048679005","https://openalex.org/W2076608692","https://openalex.org/W2117647820","https://openalex.org/W2194775991","https://openalex.org/W2296073425","https://openalex.org/W2561826558","https://openalex.org/W2577784528","https://openalex.org/W2593116425","https://openalex.org/W2759976799","https://openalex.org/W2798158991","https://openalex.org/W2810934215","https://openalex.org/W2931364255","https://openalex.org/W2936774411","https://openalex.org/W2962793908","https://openalex.org/W2963163009","https://openalex.org/W2963590343","https://openalex.org/W2963859210","https://openalex.org/W2964155802","https://openalex.org/W2964292098","https://openalex.org/W2965036688","https://openalex.org/W2982106364","https://openalex.org/W2982343573","https://openalex.org/W2982480602","https://openalex.org/W6634002929","https://openalex.org/W6637373629","https://openalex.org/W6674201379","https://openalex.org/W6677082149","https://openalex.org/W6678280073","https://openalex.org/W6691895530","https://openalex.org/W6733814495","https://openalex.org/W6736098614","https://openalex.org/W6751420435","https://openalex.org/W6751647823","https://openalex.org/W6751883947","https://openalex.org/W6753583920","https://openalex.org/W6753772092","https://openalex.org/W6753847621","https://openalex.org/W6756539195","https://openalex.org/W6758632346","https://openalex.org/W6763073069","https://openalex.org/W6764051988"],"related_works":[],"abstract_inverted_index":{"High":[0],"quality":[1],"labeled":[2,50,126],"datasets":[3,173],"have":[4],"allowed":[5],"deep":[6,42],"learning":[7,138],"to":[8,21,47,68,148,160],"achieve":[9],"impressive":[10],"results":[11,178],"on":[12,139],"many":[13],"sound":[14],"analysis":[15],"tasks.":[16],"Yet,":[17],"it":[18],"is":[19,158],"labor-intensive":[20],"accurately":[22],"annotate":[23],"large":[24],"amount":[25],"of":[26,53,89,97,106,165],"audio":[27,75,171],"data,":[28],"and":[29,82,104,116,141,175,196],"the":[30,37,41,70,87,98,102,112,123,129,136,151,162,170,180,199],"dataset":[31,113],"may":[32],"contain":[33],"noisy":[34,71,117,130,142],"labels":[35,72],"in":[36],"practical":[38],"settings.":[39],"Meanwhile,":[40],"neural":[43,108],"networks":[44],"are":[45,84],"susceptive":[46],"those":[48],"incorrect":[49,166],"data":[51,127],"because":[52],"their":[54],"outstanding":[55],"memorization":[56],"ability.":[57],"In":[58],"this":[59],"article,":[60],"we":[61,110],"present":[62],"a":[63],"novel":[64],"framework,":[65],"named":[66],"CrossFilter,":[67],"combat":[69],"problem":[73],"for":[74,92],"tagging.":[76],"Multiple":[77],"representations":[78],"(such":[79],"as,":[80],"Logmel":[81],"MFCC)":[83],"used":[85],"as":[86],"input":[88],"our":[90,133,191],"framework":[91],"providing":[93],"more":[94],"complementary":[95],"information":[96],"audio.":[99],"Then,":[100],"though":[101],"cooperation":[103],"interaction":[105],"two":[107],"networks,":[109],"divide":[111],"into":[114],"curated":[115,140],"subsets":[118,143],"by":[119],"incrementally":[120],"pick":[121],"out":[122],"possibly":[124],"correctly":[125],"from":[128],"data.":[131],"Moreover,":[132],"approach":[134],"leverages":[135],"multi-task":[137],"with":[144,184],"different":[145],"loss":[146,156],"function":[147,157],"fully":[149],"utilize":[150],"entire":[152],"dataset.":[153],"The":[154],"noisy-robust":[155],"employed":[159],"alleviate":[161],"adverse":[163],"effects":[164],"labels.":[167],"On":[168,188],"both":[169],"tagging":[172],"FSDKaggle2018":[174,189],"FSDKaggle2019,":[176],"empirical":[177],"demonstrate":[179],"performance":[181,195],"improvement":[182],"compared":[183],"other":[185],"competing":[186],"approaches.":[187],"dataset,":[190],"method":[192],"achieves":[193],"state-of-the-art":[194],"even":[197],"surpasses":[198],"ensemble":[200],"models.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2020-07-23T00:00:00"}