{"id":"https://openalex.org/W3096407601","doi":"https://doi.org/10.1109/icassp39728.2021.9414371","title":"BW-EDA-EEND: streaming END-TO-END Neural Speaker Diarization for a Variable Number of Speakers","display_name":"BW-EDA-EEND: streaming END-TO-END Neural Speaker Diarization for a Variable Number of Speakers","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3096407601","doi":"https://doi.org/10.1109/icassp39728.2021.9414371","mag":"3096407601"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/2011.02678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005681147","display_name":"Eun\u2010Jung Han","orcid":"https://orcid.org/0000-0002-8385-3775"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]},{"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":["DE","US"],"is_corresponding":true,"raw_author_name":"Eunjung Han","raw_affiliation_strings":["Amazon Alexa Speech, Sunnyvale, CA, USA","Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa Speech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056081738","display_name":"Chul Lee","orcid":"https://orcid.org/0000-0001-9329-7365"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]},{"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":["DE","US"],"is_corresponding":false,"raw_author_name":"Chul Lee","raw_affiliation_strings":["Amazon Alexa Speech, Sunnyvale, CA, USA","Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa Speech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"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"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":["Amazon Alexa Speech, Sunnyvale, CA, USA","Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa Speech, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005681147"],"corresponding_institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":0.28220715,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60041001,"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":"7193","last_page":"7197"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998000264167786,"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":0.7152606844902039},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6308881044387817},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6067653894424438},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5842653512954712},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5713787078857422},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4995267391204834},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.481845498085022},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33891379833221436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2746339738368988},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.26082608103752136},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09178587794303894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7152606844902039},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6308881044387817},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6067653894424438},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5842653512954712},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5713787078857422},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4995267391204834},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.481845498085022},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33891379833221436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2746339738368988},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.26082608103752136},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09178587794303894},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.02678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02678","pdf_url":"https://arxiv.org/pdf/2011.02678","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:3096407601","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.02678.pdf","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.2011.02678","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.02678","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"},{"id":"doi:10.17023/ry1a-s877","is_oa":true,"landing_page_url":"https://doi.org/10.17023/ry1a-s877","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.02678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02678","pdf_url":"https://arxiv.org/pdf/2011.02678","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1965819578","https://openalex.org/W2150769028","https://openalex.org/W2219249508","https://openalex.org/W2558649592","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2746574320","https://openalex.org/W2890964092","https://openalex.org/W2891247151","https://openalex.org/W2896538040","https://openalex.org/W2900212944","https://openalex.org/W2900440209","https://openalex.org/W2939690918","https://openalex.org/W2962788625","https://openalex.org/W2963470929","https://openalex.org/W2964110616","https://openalex.org/W2981608174","https://openalex.org/W3007946293","https://openalex.org/W3008357631","https://openalex.org/W3015780472","https://openalex.org/W3016232124","https://openalex.org/W3033627755","https://openalex.org/W3095212884","https://openalex.org/W6688816777","https://openalex.org/W6769530546","https://openalex.org/W6779069803"],"related_works":["https://openalex.org/W3162770427","https://openalex.org/W3123299152","https://openalex.org/W3128434617","https://openalex.org/W2400927397","https://openalex.org/W2187162700","https://openalex.org/W2404175974","https://openalex.org/W2177420620","https://openalex.org/W2587150483","https://openalex.org/W3095950464","https://openalex.org/W2951343470","https://openalex.org/W3015194534","https://openalex.org/W2952783970","https://openalex.org/W3015927303","https://openalex.org/W3034497445","https://openalex.org/W3007528493","https://openalex.org/W3024231486","https://openalex.org/W3012459487","https://openalex.org/W2936794852","https://openalex.org/W3105669983","https://openalex.org/W2368062854"],"abstract_inverted_index":{"We":[0,67],"present":[1],"a":[2,15,91,119],"novel":[3],"online":[4,110],"end-to-end":[5],"neural":[6],"diarization":[7,123,149],"system,":[8],"BW-EDA-EEND,":[9,73,146],"that":[10],"processes":[11,75],"data":[12],"incrementally":[13],"for":[14,85,125],"variable":[16],"number":[17],"of":[18,29,94,141],"speakers.":[19],"The":[20],"system":[21,124],"is":[22],"based":[23],"on":[24],"the":[25,35,50,61,106,115,160],"Encoder-Decoder-Attractor":[26],"(EDA)":[27],"architecture":[28],"Horiguchi":[30],"et":[31],"al.,":[32],"but":[33,114],"utilizes":[34],"incremental":[36],"Transformer":[37],"encoder,":[38],"attending":[39],"only":[40,82],"to":[41,53,58,87,98,127,159],"its":[42],"left":[43],"contexts":[44],"and":[45,111,134],"using":[46,90],"block-level":[47],"recurrence":[48],"in":[49,65,77],"hidden":[51],"states":[52],"carry":[54],"information":[55],"from":[56],"block":[57],"block,":[59],"making":[60],"algorithm":[62,116],"complexity":[63],"linear":[64,78],"time.":[66],"propose":[68],"two":[69,88,104],"variants:":[70],"For":[71,144],"unlimited-latency":[72],"which":[74,147],"inputs":[76],"time,":[79],"we":[80,155],"show":[81,156],"moderate":[83],"degradation":[84],"up":[86],"speakers":[89,129],"context":[92,132,139],"size":[93,140],"10":[95,142],"seconds":[96],"compared":[97],"offline":[99,112,121,161],"EDA-EEND.":[100],"With":[101],"more":[102],"than":[103],"speakers,":[105],"accuracy":[107,137,157],"gap":[108],"between":[109],"grows,":[113],"still":[117],"outperforms":[118],"baseline":[120],"clustering":[122],"one":[126],"four":[128],"with":[130,138],"unlimited":[131],"size,":[133],"shows":[135],"comparable":[136,158],"seconds.":[143],"limited-latency":[145],"produces":[148],"outputs":[150],"block-by-block":[151],"as":[152],"audio":[153],"arrives,":[154],"clustering-based":[162],"system.":[163]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}