{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:14:06Z","timestamp":1740172446567,"version":"3.37.3"},"reference-count":59,"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":[{"DOI":"10.13039\/501100001849","name":"Defence Research and Development Organisation","doi-asserted-by":"publisher","award":["CSE1314142DRDOHEMA"],"award-info":[{"award-number":["CSE1314142DRDOHEMA"]}],"id":[{"id":"10.13039\/501100001849","id-type":"DOI","asserted-by":"publisher"}]}],"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.2020.3036231","type":"journal-article","created":{"date-parts":[[2020,11,5]],"date-time":"2020-11-05T20:32:37Z","timestamp":1604608357000},"page":"14-27","source":"Crossref","is-referenced-by-count":11,"title":["Novel Architectures for Unsupervised Information Bottleneck Based Speaker Diarization of Meetings"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1592-6300","authenticated-orcid":false,"given":"Nauman","family":"Dawalatabad","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4361-784X","authenticated-orcid":false,"given":"Srikanth","family":"Madikeri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5551-4883","authenticated-orcid":false,"given":"C. Chandra","family":"Sekhar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hema A.","family":"Murthy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"article-title":"Neural predictive coding using convolutional neural networks towards unsupervised learning of speaker characteristics","year":"2018","author":"jati","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683373"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1650"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref36"},{"journal-title":"Handbook Of Research On Machine Learning Applications and Trends Algorithms Methods and Techniques - 2 Volumes","year":"2009","author":"olivas","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683114"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"year":"0","key":"ref2","article-title":"IBM Watson: Who's speaking? : Speaker Diarization with Watson Speech-to-Text API"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078608"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953194"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-270"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref50","first-page":"2170","article-title":"DiarTk: An open source toolkit for research in multistream speaker diarization and its application to meetings recordings","author":"vijayasenan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref51","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref59","first-page":"3105","article-title":"Integrating online I-vector extractor with information bottleneck based speaker diarization system","author":"madikeri","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref58","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853564"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.1991.176402"},{"key":"ref53","first-page":"321","author":"rokach","year":"2005","journal-title":"CLUSTERING METHODS"},{"key":"ref52","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc Thirteenth Int Conf Artif Intell Statist"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2747097"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1364"},{"key":"ref40","article-title":"The information bottleneck method","author":"tishby","year":"1998","journal-title":"NEC Res Insti"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1947"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1203"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853568"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/NCC.2016.7561127"},{"key":"ref16","first-page":"945","article-title":"Exploiting intra-conversation variability for speaker diarization","author":"shum","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178889"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/EEEI.2012.6376948"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-572"},{"key":"ref4","first-page":"1059","article-title":"KL realignment for speaker diarization with multiple feature streams","author":"vijayasenan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015698"},{"article-title":"Improving real time factor of information bottleneck-based speaker diarization system","year":"2015","author":"madikeri","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2048603"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-714"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639170"},{"year":"0","key":"ref49","article-title":"The NIST rich transcription"},{"journal-title":"Pattern Recognition and Machine Learning (Inf Science and Stat )","year":"2006","author":"bishop","key":"ref9"},{"year":"0","key":"ref46","article-title":"Linguistic data consortium"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-411"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"year":"0","key":"ref42","article-title":"BUT phoneme recognizer"},{"key":"ref41","first-page":"1","article-title":"Musical onset detection on carnatic percussion instruments","author":"kumar","year":"0","journal-title":"Proc Twenty First Nat Conf Commun"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2159710"},{"journal-title":"Digital Processing of Speech Signals","year":"1978","author":"rabiner","key":"ref43"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09250017.pdf?arnumber=9250017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:54Z","timestamp":1652194434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9250017\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.3036231","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2021]]}}}