{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:16:37Z","timestamp":1776442597642,"version":"3.51.2"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/apsipaasc47483.2019.9023039","type":"proceedings-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T17:03:54Z","timestamp":1583514234000},"page":"1652-1656","source":"Crossref","is-referenced-by-count":105,"title":["Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition"],"prefix":"10.1109","author":[{"given":"Xu","family":"Xiang","sequence":"first","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, SpeechLab, Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, SpeechLab, Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Houjun","family":"Huang","sequence":"additional","affiliation":[{"name":"AISpeech Co., Ltd.,China"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, SpeechLab, Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}]},{"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, SpeechLab, Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"}]}],"member":"263","reference":[{"key":"ref10","first-page":"5265","article-title":"Cosface: Large margin cosine loss for deep face recognition","author":"wang","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref12","article-title":"Arcface: Additive angular margin loss for deep face recognition","author":"deng","year":"2019","journal-title":"The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref13","author":"povey","year":"2011","journal-title":"The Kaldi Speech Recognition Toolkit"},{"key":"ref14","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"NIPS-W"},{"key":"ref15","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":"Proc Speaker Odyssey"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1545"},{"key":"ref17","first-page":"499","article-title":"A discriminative feature learning approach for deep face recognition","author":"wen","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1041","DOI":"10.1145\/3123266.3123359","article-title":"Normface: L2 hypersphere embedding for face verification","author":"wang","year":"2017","journal-title":"Proc 25th ACM Int Conf Multimedia"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"2616","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1007\/11744085_41","article-title":"Probabilistic linear discriminant analysis","author":"ioffe","year":"2006","journal-title":"Proc European Conference on Computer Vision 2006"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"999","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1487","DOI":"10.21437\/Interspeech.2017-1608","article-title":"End-to-end text-independent speaker verification with triplet loss on short utterances","author":"zhang","year":"2017","journal-title":"InterSpeech"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462508"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846261"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1109\/SLT.2016.7846260","article-title":"Deep neural network-based speaker embeddings for end-to-end speaker verification","author":"snyder","year":"2016","journal-title":"Spoken Language Technology Workshop (SLT) IEEE"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1129"},{"key":"ref22","author":"hajibabaei","year":"2018","journal-title":"Unified hypersphere embedding for speaker recognition"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref26","author":"goyal","year":"2017","journal-title":"Accurate large minibatch sgd Training imagenet in 1 hour"},{"key":"ref25","author":"sergeev","year":"2018","journal-title":"Horovod fast and easy distributed deep learning in tensorflow"}],"event":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Lanzhou, China","start":{"date-parts":[[2019,11,18]]},"end":{"date-parts":[[2019,11,21]]}},"container-title":["2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8989870\/9023008\/09023039.pdf?arnumber=9023039","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T19:18:30Z","timestamp":1734635910000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9023039\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc47483.2019.9023039","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}