{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:46:02Z","timestamp":1765039562356,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383502","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"567-573","source":"Crossref","is-referenced-by-count":6,"title":["Look Who\u2019s Not Talking"],"prefix":"10.1109","author":[{"given":"Youngki","family":"Kwon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hee Soo","family":"Heo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaesung","family":"Huh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bong-Jin","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF01890115"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"VoxCeleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"InterSpeech"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.21437\/Odyssey.2018-11","article-title":"Exploring the encoding layer and loss function in end-to-end speaker and language recognition system","author":"cai","year":"2018","journal-title":"Speaker Odyssey"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Sgdr: Stochastic gradient descent with warm restarts","year":"2016","author":"loshchilov","key":"ref37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1903"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639150"},{"key":"ref13","first-page":"4828","article-title":"Full-covariance ubm and heavy-tailed plda in i-vector speaker verification","author":"mat?jka","year":"2011","journal-title":"Proc ICASSP"},{"key":"ref14","first-page":"4052","article-title":"Deep neural networks for small footprint text-dependent speaker verification","author":"variani","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404844"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"999","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embed-dings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref17","article-title":"X-vectors: Ro-bust dnn embeddings for speaker recognition","author":"snyder","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref18","article-title":"A spectral clustering approach to speaker diarization","author":"ning","year":"2006","journal-title":"Ninth International Conference on Spoken Language Processing"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"article-title":"Confidence estimation in deep neural networks via density modelling","year":"2017","author":"subramanya","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637694"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298891"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/89.848229"},{"journal-title":"WebRTC APIs and RTCWEB Protocols of the HTML5 Real-Time Web","year":"2012","author":"johnston","key":"ref6"},{"article-title":"Instance normalization: The missing ingredient for fast stylization","year":"2016","author":"ulyanov","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461921"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1742"},{"key":"ref7","article-title":"Bob speaks kaldi","author":"cernak","year":"2017","journal-title":"InterSpeech"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1109\/TSA.2005.851909","article-title":"Robust end-point detection algorithm based on the adaptive band-partitioning spectral entropy in adverse environments","volume":"13","author":"wu","year":"2005","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.905996"},{"year":"2019","key":"ref46","article-title":"DIHARD 2019 baseline"},{"key":"ref20","first-page":"4930","article-title":"Speaker diarization using deep neural network embeddings","author":"garcia-romero","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3116"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078610"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461546"},{"key":"ref42","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref41","first-page":"428","article-title":"Nist rt’05s evaluation: pre-processing techniques and speaker di-arization on multiple microphone meetings","author":"istrate","year":"2005","journal-title":"5th International Workshop on Machine Learning for Multimodal Interaction"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"2739","DOI":"10.21437\/Interspeech.2017-166","article-title":"Developing online speaker diarization system","author":"dimitriadis","year":"2017","journal-title":"InterSpeech"},{"key":"ref44","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Workshop on Multi-view Lip-reading ACCV"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref43","article-title":"Spot the conversation: speaker diarisation in the wild","author":"chung","year":"2020","journal-title":"INTER-SPEECH"},{"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\/09383502.pdf?arnumber=9383502","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T21:31:03Z","timestamp":1622496663000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383502\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383502","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}