{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:14:13Z","timestamp":1776885253310,"version":"3.51.2"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"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":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533489","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T17:27:41Z","timestamp":1632158861000},"page":"1-7","source":"Crossref","is-referenced-by-count":5,"title":["Contrastive Learning for improving End-to-end Speaker Verification"],"prefix":"10.1109","author":[{"given":"Yanxi","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyang","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref38","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref33","article-title":"Training convolutional networks with noisy labels","author":"sukhbaatar","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref32","article-title":"Generalized cross entropy loss for training deep neural networks with noisy labels","author":"zhang","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref31","first-page":"3","article-title":"Accelerated learning in layered neural networks","volume":"2","author":"levin","year":"1988","journal-title":"Complex Systems"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref37","article-title":"When does label smoothing help?","author":"m\u00fcller","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref35","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","author":"cao","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref34","article-title":"Cross-entropy loss and low-rank features have responsibility for adversarial examples","author":"nar","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref28","article-title":"Locally-connected and convolutional neural networks for small footprint speaker recognition","author":"chen","year":"0","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.07.003"},{"key":"ref29","article-title":"Multi-task learning for text-dependent speaker verification","author":"chen","year":"0","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/5.628714"},{"key":"ref20","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref22","article-title":"Supervised contrastive learning","author":"khosla","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref21","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref24","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","volume":"2014","author":"kenny","year":"2014","journal-title":"Odyssey"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21236\/ADA613971"},{"key":"ref26","article-title":"A unified deep neural network for speaker and language recognition","author":"richardson","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Tandem deep features for text-dependent speaker verification","author":"fu","year":"0","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref50","article-title":"Distance metric learning for large margin nearest neighbor classification","volume":"10","author":"weinberger","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2275"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref11","first-page":"5359","article-title":"Attention-based models for text-dependent speaker verification","author":"chowdhury","year":"0","journal-title":"2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref40","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846261"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682676"},{"key":"ref14","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref16","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref17","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref19","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref5","article-title":"Faster r-cnn: Towards realtime object detection with region proposal networks","author":"ren","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref49","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"he","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref9","article-title":"Deep speaker: an end-to-end neural speaker embedding system","volume":"650","author":"li","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref46","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","author":"gutmann","year":"0","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics JMLR Workshop and Conference Proceedings"},{"key":"ref45","article-title":"Learning deep representations by mutual information estimation and maximization","author":"hjelm","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref48","first-page":"1857","article-title":"Improved deep metric learning with multi-class n-pair loss objective","author":"sohn","year":"0","journal-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems"},{"key":"ref47","first-page":"2265","article-title":"Learning word embeddings efficiently with noise-contrastive estimation","volume":"26","author":"mnih","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref41","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref44","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"henaff","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","location":"Shenzhen, China","start":{"date-parts":[[2021,7,18]]},"end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533489.pdf?arnumber=9533489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T14:44:33Z","timestamp":1673275473000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533489\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533489","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}