{"id":"https://openalex.org/W4406858523","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848831","title":"EEND-EM: End-to-End Neural Speaker Diarization with EM-Network","display_name":"EEND-EM: End-to-End Neural Speaker Diarization with EM-Network","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858523","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848831"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003903797","display_name":"Beom Jun Woo","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Beom Jun Woo","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016783920","display_name":"Ji Won Yoon","orcid":"https://orcid.org/0000-0001-8631-4489"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ji Won Yoon","raw_affiliation_strings":["Chung-Ang University,Department of Artificial Intelligence,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chung-Ang University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009851092","display_name":"Min Hyun Han","orcid":"https://orcid.org/0000-0002-8086-5009"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Min Hyun Han","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052669348","display_name":"Chan Hee Moon","orcid":"https://orcid.org/0000-0003-1393-0242"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chan Yeong Moon","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112750451","display_name":"Nam Soo Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Department of Electrical and Computer Engineering and INMC,Seoul,Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9947999715805054,"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":0.9947999715805054,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9232000112533569,"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":0.6834617853164673},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6752752065658569},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6468404531478882},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46602487564086914},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.456320583820343},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3476846218109131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21470606327056885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6834617853164673},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6752752065658569},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6468404531478882},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46602487564086914},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.456320583820343},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3476846218109131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21470606327056885}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10848831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":12,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2891833136","https://openalex.org/W2962780374","https://openalex.org/W2997419692","https://openalex.org/W3025260599","https://openalex.org/W3190394743","https://openalex.org/W4220731890","https://openalex.org/W4372260091","https://openalex.org/W4375869221","https://openalex.org/W4385573729","https://openalex.org/W6766883552","https://openalex.org/W6767725219"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"In":[0,31],"recent":[1],"years,":[2],"various":[3],"studies":[4],"have":[5],"been":[6],"conducted":[7],"to":[8,58,108],"further":[9],"enhance":[10,59],"end-to-end":[11,39],"neural":[12,40],"speaker":[13,41],"diarization":[14,42,60,92],"(EEND)":[15],"systems.":[16],"However":[17],"most":[18],"of":[19],"the":[20,52,69,73,84,109,119],"methods":[21],"increase":[22],"model":[23,43,79],"complexity":[24],"by":[25,62],"requiring":[26],"additional":[27],"modules":[28],"during":[29],"inference.":[30],"this":[32],"paper,":[33],"we":[34],"introduce":[35],"EEND-EM,":[36],"a":[37],"novel":[38],"that":[44,118],"integrates":[45],"an":[46],"EM":[47,70],"algorithm-aware":[48],"self-distillation":[49],"method":[50],"into":[51],"EEND":[53],"framework.":[54],"Our":[55],"approach":[56],"aims":[57],"performance":[61],"utilizing":[63],"oracle":[64],"guidance":[65],"features":[66],"derived":[67],"from":[68],"algorithm,":[71],"improving":[72],"model\u2019s":[74],"prediction":[75],"accuracy":[76],"without":[77],"increasing":[78],"complexity.":[80],"Through":[81],"experiments":[82],"on":[83],"LibriMix":[85],"dataset,":[86],"EEND-EM":[87,123],"demonstrated":[88],"significant":[89],"improvements":[90],"in":[91,97,122],"error":[93],"rates":[94],"(DER),":[95],"particularly":[96],"minimizing":[98],"missed":[99],"speech":[100],"(MS)":[101],"and":[102],"confusion":[103],"(CF)":[104],"metrics,":[105],"when":[106],"compared":[107],"baseline":[110],"EEND-EDA":[111],"model.":[112],"Furthermore,":[113],"attention":[114],"weight":[115],"visualizations":[116],"indicate":[117],"transformer":[120],"encoders":[121],"are":[124],"trained":[125],"more":[126],"effectively.":[127]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}