{"id":"https://openalex.org/W3095994161","doi":"https://doi.org/10.21437/interspeech.2020-2329","title":"An Effective Perturbation Based Semi-Supervised Learning Method for Sound Event Detection","display_name":"An Effective Perturbation Based Semi-Supervised Learning Method for Sound Event Detection","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095994161","doi":"https://doi.org/10.21437/interspeech.2020-2329","mag":"3095994161"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2329","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/An_effective_perturbation_based_semi-supervised_learning_method_for_sound_event_detection/24217365","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087416701","display_name":"Xu Zheng","orcid":"https://orcid.org/0000-0002-9733-6795"},"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":"Xu Zheng","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"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":"Yan Song","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101437836","display_name":"Jie Yan","orcid":"https://orcid.org/0000-0001-9512-322X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"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":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"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"]},{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["ICT Cluster, Singapore Institute of Technology, Singapore","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICT Cluster, Singapore Institute of Technology, Singapore","institution_ids":["https://openalex.org/I168639165"]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100383321","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0002-8773-6162"},"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":"Lin Liu","raw_affiliation_strings":["iFLYTEK Research, iFLYTEK CO., LTD, Hefei, China","National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, iFLYTEK CO., LTD, Hefei, China","institution_ids":[]},{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"841","last_page":"845"},"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":0.9994999766349792,"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":0.9934999942779541,"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":0.6923869252204895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5409402251243591},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5273075103759766},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5233135223388672},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.48723331093788147},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4468020796775818},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.44571825861930847},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.445382297039032},{"id":"https://openalex.org/keywords/standard-deviation","display_name":"Standard deviation","score":0.4426061511039734},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3933110535144806},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32187870144844055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1813100278377533},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1598626673221588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6923869252204895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5409402251243591},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5273075103759766},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5233135223388672},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.48723331093788147},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4468020796775818},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.44571825861930847},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.445382297039032},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.4426061511039734},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3933110535144806},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32187870144844055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1813100278377533},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1598626673221588},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-2329","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/24217365","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/An_effective_perturbation_based_semi-supervised_learning_method_for_sound_event_detection/24217365","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/24217365","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/An_effective_perturbation_based_semi-supervised_learning_method_for_sound_event_detection/24217365","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference contribution"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.6499999761581421,"display_name":"Climate action"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1498369575","https://openalex.org/W1522301498","https://openalex.org/W1548802052","https://openalex.org/W1836465849","https://openalex.org/W1970578576","https://openalex.org/W2043194666","https://openalex.org/W2079057609","https://openalex.org/W2095705004","https://openalex.org/W2147917435","https://openalex.org/W2403149086","https://openalex.org/W2408239454","https://openalex.org/W2624241755","https://openalex.org/W2890166761","https://openalex.org/W2936774411","https://openalex.org/W2939641110","https://openalex.org/W2948847012","https://openalex.org/W2949117887","https://openalex.org/W2951970475","https://openalex.org/W2952634764","https://openalex.org/W2953070460","https://openalex.org/W2962734576","https://openalex.org/W2963420686","https://openalex.org/W2963558289","https://openalex.org/W2963723765","https://openalex.org/W2964159205","https://openalex.org/W3015792128","https://openalex.org/W4288356534","https://openalex.org/W4289329167","https://openalex.org/W4309845474"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W10944326","https://openalex.org/W2001391081"],"abstract_inverted_index":{"<p":[0],"dir=\"ltr\">Mean":[1],"teacher":[2,33,61],"based":[3,50,57,105],"methods":[4,34],"are":[5],"increasingly":[6],"achieving":[7,162],"state-of-the-art":[8],"performance":[9],"for":[10,75],"large-scale":[11,37],"weakly":[12],"labeled":[13],"and":[14,86,119],"unlabeled":[15,38],"sound":[16],"event":[17],"detection":[18],"(SED)":[19],"tasks":[20],"in":[21,40],"recent":[22],"DCASE":[23],"challenges.":[24],"By":[25],"penalizing":[26],"inconsistent":[27],"predictions":[28],"under":[29],"different":[30,76,130],"perturbations,":[31],"mean":[32,60],"can":[35,93,133],"exploit":[36],"data":[39],"a":[41,64,81,173],"self-ensembling":[42],"manner.":[43],"In":[44],"this":[45],"paper,":[46],"an":[47,135],"effective":[48,136],"perturbation":[49],"semi-supervised":[51],"learning":[52],"(SSL)":[53],"method":[54],"is":[55,70,108],"proposed":[56,71,90,110,160],"on":[58,148],"the":[59,116,142,152,156,159,167],"method.":[62],"Specifically,":[63],"new":[65],"independent":[66],"component":[67],"(IC)":[68],"module":[69,92,107],"to":[72,98,111,139],"introduce":[73],"perturbations":[74],"convolutional":[77],"layers,":[78],"designed":[79],"as":[80],"combination":[82],"of":[83,151,158],"batch":[84],"normalization":[85],"dropblock":[87],"operations.":[88],"The":[89],"IC":[91],"reduce":[94],"correlation":[95],"between":[96,115],"neurons":[97],"improve":[99],"performance.":[100],"A":[101],"global":[102],"statistics":[103,122],"pooling":[104],"attention":[106,137],"further":[109],"explicitly":[112],"model":[113],"inter-dependencies":[114],"time-frequency":[117],"domain":[118],"channels,":[120],"using":[121],"information":[123],"(e.g.":[124],"mean,":[125],"standard":[126],"deviation,":[127],"max)":[128],"along":[129],"dimensions.":[131],"This":[132],"provide":[134],"mechanism":[138],"adaptively":[140],"re-calibrate":[141],"output":[143],"feature":[144],"map.":[145],"Experimental":[146],"results":[147],"Task":[149],"4":[150],"DCASE2018":[153],"challenge":[154],"demonstrate":[155],"superiority":[157],"method,":[161],"about":[163],"39.8%":[164],"F1-score,":[165],"outperforming":[166],"previous":[168],"winning":[169],"system\u2019s":[170],"32.4%":[171],"by":[172],"significant":[174],"margin.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}