{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:37Z","timestamp":1760245057158,"version":"3.44.0"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683373","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"5801-5805","source":"Crossref","is-referenced-by-count":20,"title":["Speaker Diarisation Using 2D Self-attentive Combination of Embeddings"],"prefix":"10.1109","author":[{"given":"G.","family":"Sun","sequence":"first","affiliation":[{"name":"Cambridge University Engineering Dept, Trumpington St, Cambridge, CB2 1PZ, U.K."}]},{"given":"C.","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cambridge University Engineering Dept, Trumpington St, Cambridge, CB2 1PZ, U.K."}]},{"given":"P. C.","family":"Woodland","sequence":"additional","affiliation":[{"name":"Cambridge University Engineering Dept, Trumpington St, Cambridge, CB2 1PZ, U.K."}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref11","article-title":"High order recurrent neural networks for acoustic modeling","author":"zhang","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015698"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-579","article-title":"DiarTk: An open source toolkit for research in multistream speaker diarization and its application to meetings recordings","author":"vijayasenan","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1545"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1688"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-714"},{"key":"ref17","article-title":"The AMI meeting corpus: A pre-announcement","author":"carletta","year":"2006","journal-title":"Proc MLMI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref19","article-title":"Speaker diarization with PLDA i-vector scoring and unsupervised calibration","author":"selland","year":"2014","journal-title":"Proc SLT"},{"key":"ref28","article-title":"Artifitial neural network features for speaker diarization","author":"yella","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref29","article-title":"A comparison of neural network feature transforms for speaker diarization","author":"yella","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref5","article-title":"Speaker diarization using deep neural network embed-dings","author":"garcia-romero","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref8","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"Proc ICLR"},{"article-title":"Speaker diarization using deep recurrent convolutional neural networks for speaker embeddings","year":"2017","author":"cyrta","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178881"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref20","article-title":"A comparison of neural network feature transforms for speaker diarization","author":"yella","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref22","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref21","article-title":"Attention-based models for text-dependent speaker verification","author":"chowdhury","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2647199"},{"key":"ref23","article-title":"End-to-End attention based text-dependent speaker verification","author":"zhang","year":"2016","journal-title":"Proc SLT"},{"journal-title":"The HTK book (for HTK version 3 5)","year":"2015","author":"young","key":"ref26"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-452","article-title":"Deep speaker feature learning for text-independent speaker verification","author":"li","year":"2017","journal-title":"Proc INTERSPEECH"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, UK","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683373.pdf?arnumber=8683373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:37:47Z","timestamp":1755909467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683373","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}