{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:46:08Z","timestamp":1765039568603,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"British Telecom Research Center"},{"name":"Department of Atomic Energy","award":["34\/20\/12\/2018-BRNS\/3408"],"award-info":[{"award-number":["34\/20\/12\/2018-BRNS\/3408"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3075100","type":"journal-article","created":{"date-parts":[[2021,4,23]],"date-time":"2021-04-23T20:38:15Z","timestamp":1619210295000},"page":"1639-1649","source":"Crossref","is-referenced-by-count":12,"title":["Self-Supervised Representation Learning With Path Integral Clustering for Speaker Diarization"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0760-8572","authenticated-orcid":false,"given":"Prachi","family":"Singh","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5779-9066","authenticated-orcid":false,"given":"Sriram","family":"Ganapathy","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"269","article-title":"End-to-end speaker diarization for an unknown number of speakers with encoder-decoder based attractors","author":"horiguchi","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288858"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288843"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref37","first-page":"945","article-title":"Exploiting intra-conversation variability for speaker diarization","author":"shum","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67220-5_10"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1416463"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2716"},{"key":"ref29","first-page":"509","article-title":"The ICSI RT07\ufffds speaker diarization system","author":"wooters","year":"0","journal-title":"Proc Multimodal Technol Perception Humans"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1268"},{"article-title":"First DIHARD challenge evaluation plan","year":"0","author":"ryant","key":"ref1"},{"key":"ref20","first-page":"15663","article-title":"Using self-supervised learning can improve model robustness and uncertainty","author":"hendrycks","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2013.04.013"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"article-title":"2000 NIST Speaker Recognition Evaluation LDC2001S97, Linguistic Data Consortium","year":"2000","author":"przybocki","key":"ref24"},{"key":"ref23","first-page":"294","article-title":"Deep self-supervised hierarchical clustering for speaker diarization","author":"singh","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-21"},{"key":"ref25","first-page":"137","article-title":"The AMI meeting corpus","author":"mccowan","year":"0","journal-title":"Proc Measuring Behav 5th Int Conf Methods Techn Behav Res Noldus Inf Technol"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683373"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683114"},{"article-title":"A study of semi-supervised speaker diarization system using gan mixture model","year":"2019","author":"pal","key":"ref55"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2961071"},{"key":"ref53","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF01890115"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2285474"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1109\/SLT48900.2021.9383617","article-title":"Discriminative neural clustering for speaker diarisation","author":"li","year":"2021"},{"key":"ref12","first-page":"249","article-title":"Analysis of i-Vector length normalization in speaker recognition systems","author":"garcia-romero","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472638"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-29"},{"key":"ref15","first-page":"2829","article-title":"Domain adaptation of PLDA models in broadcast diarization by means of unsupervised speaker clustering","author":"vi\u00f1als","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref16","first-page":"2178","article-title":"A spectral clustering approach to speaker diarization","author":"ning","year":"0","journal-title":"Proc Interspeech Int Conf Spoken Lang Process"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015698"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"article-title":"The third DIHARD diarization challenge","year":"2020","author":"ryant","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1891"},{"key":"ref49","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_31"},{"journal-title":"The elements of statistical learning - data mining inference and prediction","year":"2009","author":"hastie","key":"ref46"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.556"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806287"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.250608"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955293"},{"key":"ref41","first-page":"6504","article-title":"Speaker diarization using latent space clustering in generative adversarial network","author":"pal","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref44","article-title":"Spectralnet: Spectral clustering using deep neural networks","author":"shaham","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","first-page":"3861","article-title":"Towards k-means-friendly spaces: Simultaneous deep learning and clustering","author":"yang","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09415169.pdf?arnumber=9415169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,25]],"date-time":"2022-12-25T09:27:35Z","timestamp":1671960455000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9415169\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3075100","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2021]]}}}