{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T08:26:22Z","timestamp":1777105582443,"version":"3.51.4"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10097032","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Probabilistic Back-ends for Online Speaker Recognition and Clustering"],"prefix":"10.1109","author":[{"given":"Alexey","family":"Sholokhov","sequence":"first","affiliation":[{"name":"Federal Research Center \"Computer Science and Control\" of the Russian Academy of Sciences,Moscow,Russia"}]},{"given":"Nikita","family":"Kuzmin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}]},{"given":"Kong Aik","family":"Lee","sequence":"additional","affiliation":[{"name":"A&#x22C6;STAR,Institute for Infocomm Research,Singapore"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746688"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362113"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-303"},{"key":"ref15","first-page":"194","article-title":"The speaker partitioning problem","author":"br\u00fcmmer","year":"2010","journal-title":"Odyssey"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639168"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10055"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1586"},{"key":"ref31","first-page":"15","article-title":"NIST speaker recognition evaluation chronicles","author":"przybocki","year":"2004","journal-title":"Odyssey"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-684"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2014.05.001"},{"key":"ref32","first-page":"137","article-title":"The AMI meeting corpus","author":"mccowan","year":"2005","journal-title":"Measuring Behavior 2005 5th International Conference on Methods and Techniques in Behavioral Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687975"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-26"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref16","first-page":"2509","article-title":"Handling recordings acquired simultaneously over multiple channels with PLDA","author":"l\u00f3pez","year":"2013","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955293"},{"key":"ref23","first-page":"207","article-title":"Variational Bayesian speaker clustering","author":"valente","year":"2004","journal-title":"Odyssey"},{"key":"ref26","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref25","first-page":"27","article-title":"Variational Bayesian model selection for mixture distributions","author":"corduneanu","year":"2001","journal-title":"AISTATS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-731"},{"key":"ref22","article-title":"Links: A high-dimensional online clustering method","author":"mansfield","year":"2018"},{"key":"ref21","volume":"2","author":"mardia","year":"2000","journal-title":"Directional Statistics"},{"key":"ref28","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"ravanelli","year":"2021"},{"key":"ref27","article-title":"Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks","author":"landini","year":"2020"},{"key":"ref29","article-title":"Clova baseline system for the VoxCeleb speaker recognition challenge 2020","author":"heo","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472638"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E95.D.2469"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362757"},{"key":"ref4","first-page":"333","article-title":"Online speaker clustering","author":"liu","year":"2004","journal-title":"ICASSP"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-20"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1067"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-17"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10097032.pdf?arnumber=10097032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:52Z","timestamp":1700507212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097032","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}