{"id":"https://openalex.org/W3196781856","doi":"https://doi.org/10.21437/interspeech.2021-384","title":"Semi-Supervised Training with Pseudo-Labeling for End-To-End Neural Diarization","display_name":"Semi-Supervised Training with Pseudo-Labeling for End-To-End Neural Diarization","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196781856","doi":"https://doi.org/10.21437/interspeech.2021-384","mag":"3196781856"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-384","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5087545401","display_name":"Yuki Takashima","orcid":"https://orcid.org/0000-0001-8489-9487"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuki Takashima","raw_affiliation_strings":["Hitachi, Ltd. Research & Development Group, Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd. Research & Development Group, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["Hitachi, Ltd. Research & Development Group, Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd. Research & Development Group, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi, Ltd. Research & Development Group, Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd. Research & Development Group, Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]},{"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":"Shinji Watanabe","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA","Center for Language and Speech Processing, Johns Hopkins University, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leibny Paola Garc\u00eda Perera","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076987349","display_name":"Kenji Nagamatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Nagamatsu","raw_affiliation_strings":["Hitachi, Ltd. Research & Development Group, Japan"],"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd. Research & Development Group, Japan","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5087545401"],"corresponding_institution_ids":["https://openalex.org/I65143321"],"apc_list":null,"apc_paid":null,"fwci":0.9518,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8023734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3096","last_page":"3100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8190945982933044},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6113688349723816},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6094853281974792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5918665528297424},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.569595217704773},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5330689549446106},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5112252235412598},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4915529191493988},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4762556552886963},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4688849151134491},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.44898560643196106},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4450223743915558},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42079809308052063},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41884198784828186},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3699348270893097},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.26373642683029175},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07474955916404724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190945982933044},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6113688349723816},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6094853281974792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5918665528297424},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.569595217704773},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5330689549446106},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5112252235412598},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4915529191493988},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4762556552886963},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4688849151134491},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.44898560643196106},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4450223743915558},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42079809308052063},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41884198784828186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3699348270893097},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.26373642683029175},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07474955916404724},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-384","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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":39,"referenced_works":["https://openalex.org/W1588359339","https://openalex.org/W1965819578","https://openalex.org/W1975113979","https://openalex.org/W2027167280","https://openalex.org/W2081074144","https://openalex.org/W2124558353","https://openalex.org/W2159591770","https://openalex.org/W2165232124","https://openalex.org/W2184906052","https://openalex.org/W2189391786","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2507595414","https://openalex.org/W2746574320","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2962788625","https://openalex.org/W2963470929","https://openalex.org/W2963745998","https://openalex.org/W2972765864","https://openalex.org/W2972949456","https://openalex.org/W2973730722","https://openalex.org/W2981608174","https://openalex.org/W3004597053","https://openalex.org/W3008357631","https://openalex.org/W3015522062","https://openalex.org/W3016244460","https://openalex.org/W3025260599","https://openalex.org/W3033627755","https://openalex.org/W3095212884","https://openalex.org/W3096338464","https://openalex.org/W3128434617","https://openalex.org/W3128688470","https://openalex.org/W3140898556","https://openalex.org/W3144086690","https://openalex.org/W3162770427","https://openalex.org/W3163187953","https://openalex.org/W3196595845","https://openalex.org/W4283014282"],"related_works":["https://openalex.org/W2130553454","https://openalex.org/W3022007134","https://openalex.org/W4317548404","https://openalex.org/W2087783760","https://openalex.org/W1509924131","https://openalex.org/W3163689946","https://openalex.org/W4287890939","https://openalex.org/W2033364610","https://openalex.org/W2797776314","https://openalex.org/W2153927146"],"abstract_inverted_index":{"In":[0],"this":[1,59],"paper,":[2,60],"we":[3,61,70,89,106,141],"present":[4],"a":[5,36,57,63,86,92,129,138],"semi-supervised":[6,146],"training":[7,94],"technique":[8],"using":[9,82,113],"pseudo-labeling":[10,64],"for":[11,43,76],"end-to-end":[12],"neural":[13],"diarization":[14,132],"(EEND).The":[15],"EEND":[16,39],"system":[17],"has":[18],"shown":[19],"promising":[20],"performance":[21,99],"compared":[22,136],"with":[23,148],"traditional":[24],"clustering-based":[25],"methods,":[26],"especially":[27],"in":[28,56],"the":[29,45,80,98,108,120,143,152,158],"case":[30],"of":[31,49,85,100,110,145,154],"overlapping":[32],"speech.However,":[33],"to":[34,96,137],"get":[35],"welltuned":[37],"model,":[38],"requires":[40],"labeled":[41,114],"data":[42,84],"all":[44],"joint":[46],"speech":[47],"activities":[48],"every":[50],"speaker":[51],"at":[52],"each":[53],"time":[54],"frame":[55],"recording.In":[58],"explore":[62],"approach":[65,156],"that":[66,124],"employs":[67],"unlabeled":[68,83,116],"data.First,":[69],"propose":[71,91],"an":[72],"iterative":[73],"pseudolabel":[74],"method":[75,95],"EEND,":[77],"which":[78],"trains":[79],"model":[81,111],"target":[87],"condition.Then,":[88],"also":[90,150],"committeebased":[93],"improve":[97],"EEND.To":[101],"evaluate":[102],"our":[103,125,155],"proposed":[104,126],"method,":[105],"conduct":[107],"experiments":[109],"adaptation":[112,147],"and":[115],"data.Experimental":[117],"results":[118,144],"on":[119,157],"CALLHOME":[121],"dataset":[122],"show":[123,151],"pseudo-label":[127],"achieved":[128],"37.4%":[130],"relative":[131],"error":[133],"rate":[134],"reduction":[135],"seed":[139],"model.Moreover,":[140],"analyzed":[142],"pseudo-labeling.We":[149],"effectiveness":[153],"third":[159],"DI-HARD":[160],"dataset.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}