{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:27:21Z","timestamp":1753601241460,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688156","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:31:00Z","timestamp":1643902260000},"page":"130-137","source":"Crossref","is-referenced-by-count":3,"title":["Short-Utterance Embedding Enhancement Method Based on Time Series Forecasting Technique for Text-Independent Speaker Verification"],"prefix":"10.1109","author":[{"given":"Jeong-Hwan","family":"Choi","sequence":"first","affiliation":[{"name":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"}]},{"given":"Joon-Young","family":"Yang","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"}]},{"given":"Joon-Hyuk","family":"Chang","sequence":"additional","affiliation":[{"name":"Hanyang University,Department of Electronic Engineering,Seoul,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref31","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Proc Ad-vances in Neural Information Processing Systems"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc International Conference on Learning Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIOT.2019.00029"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2975738"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref18","first-page":"5791","article-title":"Utterance-level aggregation for speaker recognition in the wild","author":"xie","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3025941"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-58"},{"key":"ref27","first-page":"2616","article-title":"Voxceleb: a largescale speaker identification dataset","author":"nagrani","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-53"},{"key":"ref6","first-page":"5329","article-title":"X-vectors: Robust dnn embeddings for speaker recognition","author":"snyder","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref29","first-page":"812","article-title":"The speakers in the wild (sitw) speaker recognition database","author":"castan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref5","first-page":"4052","article-title":"Deep neural networks for small footprint textdependent speaker verification","author":"variani","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref8","article-title":"Deep residual learning for image recognition","author":"kaiming","year":"0","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref7","first-page":"921","article-title":"Densely connected time de-lay neural network for speaker verification","author":"yu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref9","first-page":"5189","article-title":"A novel learnable dictionary encoding layer for end-to-end language identification","author":"cai","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","article-title":"Front-end factor analysis for speaker verifi-cation","volume":"19","author":"dehak","year":"2010","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref20","first-page":"2982","article-title":"Metalearning for short utterance speaker recognition with imbalance langth pairs","author":"kye","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","first-page":"6569","article-title":"Text-independent speaker veri-fication with adversarial learning on short utterances","author":"liu","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004029"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(01)00702-0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/for.3980030312"},{"key":"ref26","article-title":"Clova baseline system for the VoxCeleb speaker recognition challenge 2020","author":"heo","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref25","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688156.pdf?arnumber=9688156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T16:41:15Z","timestamp":1652719275000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688156","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}