{"id":"https://openalex.org/W2972949456","doi":"https://doi.org/10.21437/interspeech.2019-2899","title":"End-to-End Neural Speaker Diarization with Permutation-Free Objectives","display_name":"End-to-End Neural Speaker Diarization with Permutation-Free Objectives","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972949456","doi":"https://doi.org/10.21437/interspeech.2019-2899","mag":"2972949456"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2899","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2899","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210089357","display_name":"Hitachi (United Kingdom)","ror":"https://ror.org/0097wyf31","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210089357","https://openalex.org/I65143321"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["Hitachi","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi","institution_ids":["https://openalex.org/I4210089357"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016279564","display_name":"Naoyuki Kanda","orcid":"https://orcid.org/0000-0002-8628-3288"},"institutions":[{"id":"https://openalex.org/I4210089357","display_name":"Hitachi (United Kingdom)","ror":"https://ror.org/0097wyf31","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210089357","https://openalex.org/I65143321"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Naoyuki Kanda","raw_affiliation_strings":["Hitachi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi","institution_ids":["https://openalex.org/I4210089357"]}]},{"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/I4210089357","display_name":"Hitachi (United Kingdom)","ror":"https://ror.org/0097wyf31","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210089357","https://openalex.org/I65143321"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi","institution_ids":["https://openalex.org/I4210089357"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076987349","display_name":"Kenji Nagamatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089357","display_name":"Hitachi (United Kingdom)","ror":"https://ror.org/0097wyf31","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210089357","https://openalex.org/I65143321"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kenji Nagamatsu","raw_affiliation_strings":["Hitachi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi","institution_ids":["https://openalex.org/I4210089357"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"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":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.2305,"has_fulltext":false,"cited_by_count":231,"citation_normalized_percentile":{"value":0.99076875,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4300","last_page":"4304"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9836000204086304,"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/T11309","display_name":"Music and Audio Processing","score":0.9768000245094299,"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":0.7261320948600769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.634506344795227},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6117068529129028},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.42120280861854553},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3253212571144104},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06370744109153748},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0538555383682251}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7261320948600769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.634506344795227},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6117068529129028},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.42120280861854553},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3253212571144104},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06370744109153748},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0538555383682251}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-2899","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2899","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2162158162","https://openalex.org/W1521049138","https://openalex.org/W1509309911","https://openalex.org/W2144208207","https://openalex.org/W2175373321","https://openalex.org/W2499802997","https://openalex.org/W1497807607","https://openalex.org/W1813780412","https://openalex.org/W2128773298","https://openalex.org/W2160753975"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,50],"propose":[4],"a":[5,35,48,57,63,142],"novel":[6],"end-to-end":[7,82],"neural-network-based":[8],"speaker":[9,29,42,53],"diarization":[10,43,54,70,136,147],"method.":[11],"Unlike":[12],"most":[13],"existing":[14],"methods,":[15],"our":[16,32,105],"proposed":[17,85,126,133],"method":[18,86,127,134],"does":[19],"not":[20],"have":[21],"separate":[22],"modules":[23],"for":[24],"extraction":[25],"and":[26,61,99],"clustering":[27],"of":[28,102,139,150],"representations.":[30],"Instead,":[31],"model":[33,106],"has":[34],"single":[36],"neural":[37],"network":[38],"that":[39],"directly":[40,68],"outputs":[41],"results.":[44],"To":[45],"realize":[46],"such":[47],"model,":[49],"formulate":[51],"the":[52,76,84,103,118,125,153,164],"problem":[55],"as":[56],"multi-label":[58],"classification":[59],"problem,":[60],"introduces":[62],"permutation-free":[64],"objective":[65],"function":[66],"to":[67,92],"minimize":[69],"errors":[71],"without":[72],"being":[73,90],"suffered":[74],"from":[75,89],"speaker-label":[77],"permutation":[78],"problem.":[79],"Besides":[80],"its":[81],"simplicity,":[83],"also":[87],"benefits":[88],"able":[91],"explicitly":[93],"handle":[94],"overlapping":[95],"speech":[96,130,158],"during":[97],"training":[98],"inference.":[100],"Because":[101],"benefit,":[104],"can":[107],"be":[108],"easily":[109],"trained/adapted":[110],"with":[111,156],"real-recorded":[112,157],"multi-speaker":[113,120],"conversations":[114],"just":[115],"by":[116],"feeding":[117],"corresponding":[119],"segment":[121],"labels.":[122],"We":[123],"evaluated":[124],"on":[128,163],"simulated":[129],"mixtures.":[131],"The":[132],"achieved":[135],"error":[137,148],"rate":[138,149],"12.28%,":[140],"while":[141],"conventional":[143],"clustering-based":[144],"system":[145],"produced":[146],"28.77%.":[151],"Furthermore,":[152],"domain":[154],"adaptation":[155],"provided":[159],"25.6%":[160],"relative":[161],"improvement":[162],"CALLHOME":[165],"dataset.":[166],"Our":[167],"source":[168],"code":[169],"is":[170],"available":[171],"online":[172],"at":[173],"https://github.com/hitachi-speech/EEND.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":37},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":40},{"year":2021,"cited_by_count":45},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}