{"id":"https://openalex.org/W3164674954","doi":"https://doi.org/10.1109/asru51503.2021.9688178","title":"Dive: End-to-End Speech Diarization Via Iterative Speaker Embedding","display_name":"Dive: End-to-End Speech Diarization Via Iterative Speaker Embedding","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W3164674954","doi":"https://doi.org/10.1109/asru51503.2021.9688178","mag":"3164674954"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688178","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.13802","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047639590","display_name":"Neil Zeghidour","orcid":"https://orcid.org/0000-0001-6896-3987"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Neil Zeghidour","raw_affiliation_strings":["Google Research,Brain Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050982379","display_name":"Olivier Teboul","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Olivier Teboul","raw_affiliation_strings":["Google Research,Brain Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065912572","display_name":"David Grangier","orcid":"https://orcid.org/0000-0002-8847-9532"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113520","display_name":"Brain (Germany)","ror":"https://ror.org/01gamcy45","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210113520"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"David Grangier","raw_affiliation_strings":["Google Research,Brain Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research,Brain Team","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113520"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05306163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"702","last_page":"709"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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":0.9987000226974487,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8416740894317627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7290799617767334},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6956852078437805},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6327915191650391},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6101787686347961},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6077977418899536},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.511132538318634},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.47577205300331116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30581170320510864}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8416740894317627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7290799617767334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6956852078437805},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6327915191650391},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6101787686347961},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6077977418899536},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.511132538318634},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.47577205300331116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30581170320510864},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru51503.2021.9688178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688178","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.13802","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.13802","pdf_url":"https://arxiv.org/pdf/2105.13802","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},{"id":"mag:3164674954","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2105.13802","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2105.13802","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.13802","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.13802","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.13802","pdf_url":"https://arxiv.org/pdf/2105.13802","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3164674954.pdf","grobid_xml":"https://content.openalex.org/works/W3164674954.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W1536583098","https://openalex.org/W1677182931","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2048497537","https://openalex.org/W2081074144","https://openalex.org/W2159591770","https://openalex.org/W2219249508","https://openalex.org/W2460742184","https://openalex.org/W2519091744","https://openalex.org/W2611465255","https://openalex.org/W2626778328","https://openalex.org/W2638067502","https://openalex.org/W2746574320","https://openalex.org/W2750259098","https://openalex.org/W2896538040","https://openalex.org/W2952752702","https://openalex.org/W2963470929","https://openalex.org/W2963745998","https://openalex.org/W2964121744","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3008880747","https://openalex.org/W3010196324","https://openalex.org/W3016400019","https://openalex.org/W3020336359","https://openalex.org/W3033627755","https://openalex.org/W3037383957","https://openalex.org/W3094122712","https://openalex.org/W3095082129","https://openalex.org/W3095212884","https://openalex.org/W3105169251","https://openalex.org/W3108962419","https://openalex.org/W3125596972","https://openalex.org/W3128434617","https://openalex.org/W3145204487","https://openalex.org/W3163019736","https://openalex.org/W4214556932","https://openalex.org/W6631190155","https://openalex.org/W6682889407","https://openalex.org/W6739901393","https://openalex.org/W6743299418","https://openalex.org/W6774558098","https://openalex.org/W6774687970","https://openalex.org/W6779069803","https://openalex.org/W6779752190","https://openalex.org/W6780226713","https://openalex.org/W6784053002","https://openalex.org/W6786127183","https://openalex.org/W6788275255","https://openalex.org/W6790122275"],"related_works":["https://openalex.org/W2972346374","https://openalex.org/W3010196324","https://openalex.org/W277919747","https://openalex.org/W2140192608","https://openalex.org/W2103348173","https://openalex.org/W3157070662","https://openalex.org/W3109127301","https://openalex.org/W2972956699","https://openalex.org/W3191883738","https://openalex.org/W3160044950","https://openalex.org/W2534034218","https://openalex.org/W2753324760","https://openalex.org/W2782767377","https://openalex.org/W3015678936","https://openalex.org/W3210727692","https://openalex.org/W3163929126","https://openalex.org/W3034010994","https://openalex.org/W3182885906","https://openalex.org/W110277321","https://openalex.org/W56805716"],"abstract_inverted_index":{"We":[0],"introduce":[1],"DIVE,":[2],"an":[3,14],"end-to-end":[4],"speaker":[5,24,40,63,85,98],"diarization":[6,11],"sys-tem.":[7],"DIVE":[8,79],"presents":[9],"the":[10,32,39,45,71,83,107,122,125,135],"task":[12],"as":[13],"iterative":[15],"pro-cess:":[16],"it":[17],"repeatedly":[18],"builds":[19],"a":[20,74,119],"representation":[21],"for":[22,134],"each":[23],"before":[25],"predicting":[26],"their":[27],"voice":[28,76],"activity":[29,77],"conditioned":[30],"on":[31,61,124],"ex-tracted":[33],"representations.":[34],"This":[35],"strategy":[36],"intrinsically":[37],"resolves":[38],"ordering":[41],"ambiguity":[42],"without":[43],"requiring":[44],"classi-cal":[46],"permutation":[47],"invariant":[48],"training":[49,84],"loss.":[50,78],"In":[51],"contrast":[52],"with":[53,73,128],"prior":[54],"work,":[55],"our":[56,93],"model":[57],"does":[58,80],"not":[59,81],"rely":[60],"pretrained":[62],"represen-tations":[64],"and":[65,87],"jointly":[66],"optimizes":[67],"all":[68],"parameters":[69],"of":[70],"system":[72,120],"multi-speaker":[75],"require":[82],"identities":[86],"allows":[88],"efficient":[89],"window-based":[90],"training.":[91],"Importantly,":[92],"loss":[94],"explicitly":[95],"excludes":[96],"unreliable":[97],"turn":[99],"boundaries":[100],"from":[101],"training,":[102],"which":[103],"is":[104],"adapted":[105],"to":[106,132],"standard":[108],"collar-based":[109],"Diarization":[110],"Error":[111],"Rate":[112],"(DER)":[113],"eval-uation.":[114],"Overall,":[115],"these":[116],"contributions":[117],"yield":[118],"redefining":[121],"state-of-the-art":[123],"CALLHOME":[126],"benchmark,":[127],"6.7%":[129],"DER":[130],"compared":[131],"7.8%":[133],"best":[136],"alternative.":[137]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}