{"id":"https://openalex.org/W4297841450","doi":"https://doi.org/10.21437/interspeech.2022-103","title":"Couple learning for semi-supervised sound event detection","display_name":"Couple learning for semi-supervised sound event detection","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841450","doi":"https://doi.org/10.21437/interspeech.2022-103"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-103","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-103","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5100600683","display_name":"Rui Tao","orcid":"https://orcid.org/0000-0001-6333-513X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tao Rui","raw_affiliation_strings":["Toshiba China R&D Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Toshiba China R&D Center, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351033","display_name":"Long Yan","orcid":"https://orcid.org/0000-0001-9441-0913"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Long","raw_affiliation_strings":["Toshiba China R&D Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Toshiba China R&D Center, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017058806","display_name":"Kazushige Ouchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouchi Kazushige","raw_affiliation_strings":["Toshiba China R&D Center, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Toshiba China R&D Center, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100402345","display_name":"Xiangdong Wang","orcid":"https://orcid.org/0000-0002-4226-3250"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Wang","raw_affiliation_strings":["Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology,Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100600683"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1229,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.2521327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2398","last_page":"2402"},"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":0.9939000010490417,"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/event","display_name":"Event (particle physics)","score":0.6542940139770508},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6469831466674805},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6080080270767212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.434495747089386},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4016900956630707},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22343561053276062}],"concepts":[{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6542940139770508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6469831466674805},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6080080270767212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.434495747089386},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4016900956630707},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22343561053276062},{"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:10.21437/interspeech.2022-103","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-103","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2938440247","https://openalex.org/W2982468701","https://openalex.org/W3009703289","https://openalex.org/W3095385545","https://openalex.org/W3097495228","https://openalex.org/W3109837239","https://openalex.org/W3160339728","https://openalex.org/W3160845765","https://openalex.org/W3161638288","https://openalex.org/W3193321031","https://openalex.org/W3196645599","https://openalex.org/W3197621271","https://openalex.org/W4221052594","https://openalex.org/W4230506641","https://openalex.org/W4288099153"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2909726438","https://openalex.org/W4396696052","https://openalex.org/W4402327032"],"abstract_inverted_index":{"The":[0],"recently":[1],"proposed":[2,92],"Mean":[3,43,58,63],"Teacher":[4,44,59],"method,":[5,93],"which":[6,124],"exploits":[7],"large-scale":[8],"unlabeled":[9],"data":[10,54],"in":[11,19,71],"a":[12,38,42,112],"self-ensembling":[13],"manner,":[14],"has":[15],"achieved":[16],"state-of-the-art":[17],"results":[18,79],"several":[20],"semi-supervised":[21],"learning":[22],"benchmarks.Spurred":[23],"by":[24,75],"current":[25],"achievements,":[26],"this":[27,108],"paper":[28,109],"proposes":[29],"an":[30],"effective":[31,115],"Couple":[32,130,134],"Learning":[33,131,135],"method":[34],"1":[35],"that":[36],"combines":[37],"well-trained":[39],"model":[40,49],"and":[41,114],"model.The":[45],"suggested":[46],"pseudo-labels":[47,73],"generated":[48],"(PLG)":[50],"increases":[51],"strongly-and":[52],"weakly-labeled":[53],"to":[55],"improve":[56],"the":[57,62,68,72,84,88,91,99,104,118,126,129],"method's":[60],"performance.Moreover,":[61],"Teacher's":[64],"consistency":[65],"cost":[66],"reduces":[67],"noise":[69],"impact":[70],"introduced":[74],"detection":[76],"errors.The":[77],"experimental":[78],"on":[80,98,139],"Task":[81],"4":[82],"of":[83,90,128],"DCASE2020":[85],"challenge":[86],"demonstrate":[87],"superiority":[89],"achieving":[94],"about":[95],"44.25%":[96],"F1-score":[97],"validation":[100],"set,":[101],"significantly":[102],"outperforming":[103],"baseline":[105],"system's":[106],"32.39%.furthermore,":[107],"also":[110],"propose":[111],"simple":[113],"experiment":[116],"called":[117],"Variable":[119],"Order":[120],"Input":[121],"(VOI)":[122],"experiment,":[123],"proves":[125],"significance":[127],"method.Our":[132],"developed":[133],"code":[136],"is":[137],"available":[138],"GitHub.":[140]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}