{"id":"https://openalex.org/W3172843532","doi":"https://doi.org/10.21437/interspeech.2021-1909","title":"End-to-End Neural Diarization: From Transformer to Conformer","display_name":"End-to-End Neural Diarization: From Transformer to Conformer","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3172843532","doi":"https://doi.org/10.21437/interspeech.2021-1909","mag":"3172843532"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1909","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1909","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.07167","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049503037","display_name":"Yi Chieh Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yi Chieh Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005681147","display_name":"Eun\u2010Jung Han","orcid":"https://orcid.org/0000-0002-8385-3775"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eunjung Han","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101781931","display_name":"Chul Lee","orcid":"https://orcid.org/0000-0001-5098-8529"},"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":"Chul Lee","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Amazon (United States), Seattle, United States"],"affiliations":[{"raw_affiliation_string":"Amazon (United States), Seattle, United States","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5049503037"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54000605,"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":"3081","last_page":"3085"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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/transformer","display_name":"Transformer","score":0.7062298059463501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6410184502601624},{"id":"https://openalex.org/keywords/conformational-isomerism","display_name":"Conformational isomerism","score":0.5805856585502625},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5031854510307312},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.49298831820487976},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4749332070350647},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4724845290184021},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.45732274651527405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37034013867378235},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.18139249086380005},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10968947410583496}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7062298059463501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6410184502601624},{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.5805856585502625},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5031854510307312},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.49298831820487976},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4749332070350647},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4724845290184021},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.45732274651527405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37034013867378235},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.18139249086380005},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10968947410583496},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1909","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1909","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"},{"id":"pmh:oai:arXiv.org:2106.07167","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.07167","pdf_url":"https://arxiv.org/pdf/2106.07167","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"},{"id":"mag:3172843532","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.07167","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2106.07167","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.07167","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.07167","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.07167","pdf_url":"https://arxiv.org/pdf/2106.07167","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2117278770","https://openalex.org/W2143668817","https://openalex.org/W2219249508","https://openalex.org/W2612445135","https://openalex.org/W2626778328","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2900212944","https://openalex.org/W2900440209","https://openalex.org/W2936774411","https://openalex.org/W2939690918","https://openalex.org/W2962760690","https://openalex.org/W2973730722","https://openalex.org/W3004728855","https://openalex.org/W3015780472","https://openalex.org/W3025165719"],"related_works":["https://openalex.org/W3197916665","https://openalex.org/W3144086690","https://openalex.org/W3026868282","https://openalex.org/W2972949456","https://openalex.org/W3214456683","https://openalex.org/W3158287709","https://openalex.org/W2405970501","https://openalex.org/W148683318","https://openalex.org/W1787748203","https://openalex.org/W1505639203","https://openalex.org/W3096363420","https://openalex.org/W3205878676","https://openalex.org/W1597208282","https://openalex.org/W2989378323","https://openalex.org/W3025260599","https://openalex.org/W2441093674","https://openalex.org/W2802973008","https://openalex.org/W3105031100","https://openalex.org/W2586956420","https://openalex.org/W3198522318"],"abstract_inverted_index":{"We":[0,34],"propose":[1],"a":[2,14],"new":[3],"end-to-end":[4],"neural":[5,17],"diarization":[6,114],"(EEND)":[7],"system":[8],"that":[9,19,37,67],"is":[10],"based":[11],"on":[12,151],"Conformer,":[13],"recently":[15],"proposed":[16],"architecture":[18],"combines":[20],"convolutional":[21,41],"mappings":[22],"and":[23,29,40,53,96,109,119,142],"Transformer":[24],"to":[25,78,89],"model":[26],"both":[27],"local":[28],"global":[30],"dependencies":[31],"in":[32,49,100,122],"speech.":[33],"first":[35],"show":[36],"data":[38,81,95,121],"augmentation":[39],"subsampling":[42],"layers":[43],"enhance":[44],"the":[45,50,61,68,83,91,127,138,146],"original":[46],"self-attentive":[47],"EEND":[48,70,123,132],"Transformer-based":[51,62,84,149],"EEND,":[52],"then":[54],"Conformer":[55],"gives":[56],"an":[57],"additional":[58],"gain":[59],"over":[60,137,145],"EEND.":[63],"However,":[64],"we":[65,125],"notice":[66],"Conformer-based":[69,131],"does":[71],"not":[72],"generalize":[73],"as":[74,82],"well":[75],"from":[76],"simulated":[77,94,118],"real":[79,97,120],"conversation":[80],"model.":[85],"This":[86],"leads":[87],"us":[88],"quantify":[90],"mismatch":[92,128],"between":[93,107],"speaker":[98],"behavior":[99],"terms":[101],"of":[102],"temporal":[103],"statistics":[104],"reflecting":[105],"turn-taking":[106],"speakers,":[108],"investigate":[110],"its":[111],"correlation":[112],"with":[113,130],"error.":[115],"By":[116],"mixing":[117],"training,":[124],"mitigate":[126],"further,":[129],"achieving":[133],"24%":[134],"error":[135],"reduction":[136],"baseline":[139],"SA-EEND":[140],"system,":[141,150],"10%":[143],"improvement":[144],"best":[147],"augmented":[148],"two-speaker":[152],"CALLHOME":[153],"data.":[154]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}