{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T22:41:48Z","timestamp":1780440108620,"version":"3.54.1"},"reference-count":31,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,9]]},"DOI":"10.1109\/mlsp.2016.7738816","type":"proceedings-article","created":{"date-parts":[[2016,11,10]],"date-time":"2016-11-10T21:40:41Z","timestamp":1478814041000},"page":"1-6","source":"Crossref","is-referenced-by-count":92,"title":["Speaker identification and clustering using convolutional neural networks"],"prefix":"10.1109","author":[{"given":"Yanick","family":"Lukic","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlo","family":"Vogt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oliver","family":"Durr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thilo","family":"Stadelmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2007.11.017"},{"key":"ref30","first-page":"85","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2158419"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-015-3181-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref13","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"1995","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"3366","DOI":"10.21437\/Interspeech.2013-744","article-title":"Ex-ploring convolutional neural network structures and optimization techniques for speech recognition","author":"abdel-hamid","year":"2013","journal-title":"InterSpeech"},{"key":"ref16","first-page":"1096","article-title":"Unsupervised feature learning for audio classification using convolutional deep belief networks","author":"lee","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"686","DOI":"10.21437\/Interspeech.2014-172","article-title":"Application of convolutional neural networks to speaker recognition in noisy conditions","author":"mclaren","year":"2014","journal-title":"InterSpeech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2011.2167240"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078608"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/0167-6393(95)00009-D","article-title":"Speaker identification and verification using gaussian mixture speaker models","volume":"17","author":"douglas","year":"1995","journal-title":"Speech Communication"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511754548"},{"key":"ref27","first-page":"93","article-title":"The darpa speech recognition research database: specifications and status","author":"william","year":"1986","journal-title":"Proc DARPA Workshop on Speech Recognition"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639170"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref29","article-title":"Gmm based clustering and speaker separability in the timit speech database","volume":"85","author":"morris","year":"2004","journal-title":"IEICE Transactions on Fundamentals of Communications Electronics Informatics and Systems"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1006\/dspr.1999.0361","article-title":"Speaker verification using adapted gaussian mixture models","volume":"10","author":"douglas","year":"2000","journal-title":"Digital Signal Processing"},{"key":"ref8","first-page":"151","article-title":"Features for audio and music classification","volume":"3","author":"mckinney","year":"2003","journal-title":"ISMIR"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1101","DOI":"10.21437\/Interspeech.2014-283","article-title":"Clustering-based i-vector formulation for speaker recognition","author":"lee","year":"2014","journal-title":"InterSpeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1631272.1631300"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318476"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-77592-0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362751"},{"key":"ref22","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854950"},{"key":"ref24","article-title":"Lasagne: First release","author":"dieleman","year":"2015"},{"key":"ref23","article-title":"librosa: Audio and music signal analysis in python","author":"brian","year":"2015","journal-title":"Proceedings of the 14th Python in ScienceConference"},{"key":"ref26","article-title":"The use of cohort normalized scores for speaker verification","author":"aaron","year":"1992","journal-title":"Second International Conference on Spoken Language Processing"},{"key":"ref25","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"tomas","year":"2013","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP)","location":"Vietri sul Mare, Salerno, Italy","start":{"date-parts":[[2016,9,13]]},"end":{"date-parts":[[2016,9,16]]}},"container-title":["2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7605057\/7738802\/07738816.pdf?arnumber=7738816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T10:39:40Z","timestamp":1749724780000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7738816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,9]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/mlsp.2016.7738816","relation":{},"subject":[],"published":{"date-parts":[[2016,9]]}}}