{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:06:05Z","timestamp":1767182765631,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383617","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"574-581","source":"Crossref","is-referenced-by-count":21,"title":["Discriminative Neural Clustering for Speaker Diarisation"],"prefix":"10.1109","author":[{"given":"Qiujia","family":"Li","sequence":"first","affiliation":[]},{"given":"Florian L.","family":"Kreyssig","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Philip C.","family":"Woodland","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(93)90058-4"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref33","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/S0269964800000255"},{"key":"ref30","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"Proc NIPS Deep Learning Symposium"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683851"},{"journal-title":"The HTK Book","year":"2015","author":"young","key":"ref36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462523"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-166","article-title":"Developing online speaker diarization system","author":"dimitriadis","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-566","article-title":"A spectral clustering approach to speaker diarization","author":"ning","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683373"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1685"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref18","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref28","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"Proc ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref27","article-title":"Permutation in-variant training of deep models for speaker-independent multi-talker speech separation","author":"yu","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref8","article-title":"Speaker diarization using deep neural network embed-dings","author":"garcia-romero","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404859"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref45","article-title":"Monotonic multihead attention","author":"ma","year":"2020","journal-title":"Proc ICLR"},{"key":"ref22","article-title":"SpectralNet: Spectral Clustering using Deep Neural Networks","author":"shaham","year":"2018","journal-title":"Proc ICLR"},{"key":"ref21","article-title":"The AMI meeting corpus: A pre-announcement","author":"carletta","year":"2005","journal-title":"Proc MLMI"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461809"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref41","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054176"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1126"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383617.pdf?arnumber=9383617","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T00:22:26Z","timestamp":1698106946000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383617\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383617","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}