{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T08:42:39Z","timestamp":1729672959581,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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.2019.8683445","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"6141-6145","source":"Crossref","is-referenced-by-count":19,"title":["How to Improve Your Speaker Embeddings Extractor in Generic Toolkits"],"prefix":"10.1109","author":[{"given":"Hossein","family":"Zeinali","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lukas","family":"Burget","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johan","family":"Rohdin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Themos","family":"Stafylakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Cernocky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Convolutional neural networks and x-vector embedding for DCASE2018 acoustic scene classification challenge","year":"2018","author":"zeinali","key":"ref32"},{"key":"ref31","article-title":"Acoustic scene classification using deep con-volutional neural network and multiple spectrograms fusion","author":"weiping","year":"2017","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref30","article-title":"Convolutional neural networks with binaural representations and background subtraction for acoustic scene classification","author":"han","year":"2017","journal-title":"Tech Rep DCASE2016 Challenge"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"293","DOI":"10.21437\/Odyssey.2014-44","article-title":"Deep neural networks for extracting Baum-Welch statistics for speaker recognition","author":"kenny","year":"2014","journal-title":"Proc Odyssey"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-51"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref14","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"TERSPEECH"},{"key":"ref15","article-title":"How to train your speaker embeddings extractor","author":"mclaren","year":"2018","journal-title":"Proc Odyssey Speaker Lang Recogn Workshop Les Sables d'Olonne"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-24"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref17"},{"article-title":"MU-SAN: A music, speech, and noise corpus","year":"2015","author":"snyder","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1137"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2694708"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref3","article-title":"Language recognition via i-vectors and dimensionality reduction","author":"dehak","year":"2011","journal-title":"Twelfth Annual Conference of the International Speech Communication Association"},{"key":"ref6","article-title":"On-line signature verification using i-vector representation","author":"zeinali","year":"2017","journal-title":"IET Biometrics"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.04.005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-31"},{"key":"ref7","article-title":"Preliminary investigation of Boltz-mann machine classifiers for speaker recognition","author":"stafylakis","year":"2012","journal-title":"Odyssey 2012-The Speaker and Language Recognition Workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853887"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","year":"2015","author":"ioffe","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref21","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref24","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"30","author":"maas","year":"2013","journal-title":"Proc ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"article-title":"Attention-based models for text-dependent speaker verification","year":"2017","author":"chowdhury","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","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\/08683445.pdf?arnumber=8683445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T01:36:00Z","timestamp":1663292160000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683445\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683445","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}