{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:55:31Z","timestamp":1730199331542,"version":"3.28.0"},"reference-count":41,"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\/asru51503.2021.9687970","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:31:00Z","timestamp":1643902260000},"page":"198-205","source":"Crossref","is-referenced-by-count":0,"title":["Improving Text-Independent Speaker Verification with Auxiliary Speakers Using Graph"],"prefix":"10.1109","author":[{"given":"Jingyu","family":"Li","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong"}]},{"given":"Si-Ioi","family":"Ng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong"}]},{"given":"Tan","family":"Lee","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref39","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref38","first-page":"5220","article-title":"A study on data augmentation of reverberant speech for robust speech recognition","author":"tom","year":"0","journal-title":"Proc of ICASSP"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.21437\/Interspeech.2020-2031"},{"key":"ref32","article-title":"librosa: Audio and music signal analysis in python","volume":"8","author":"brian","year":"0","journal-title":"Proceedings of the 14th Python in Science Conference"},{"year":"1995","author":"aldous","journal-title":"Reversible Markov Chains and Random Walks on Graphs","key":"ref31"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/ICASSP39728.2021.9414057"},{"key":"ref37","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref36","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2016","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/CVPR.2018.00552"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref40","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc of NIPS"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.21437\/Interspeech.2019-1606"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.21437\/Interspeech.2019-2357"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref14","article-title":"Voxceleb: Large-scale speaker verification in the wild","author":"nagrani","year":"2019","journal-title":"Computer Science and Language"},{"key":"ref15","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Graph attention networks","author":"veli?kovi?","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Few-shot learning with graph neural networks","author":"garcia","year":"0","journal-title":"Proc of ICLR"},{"key":"ref18","first-page":"858","article-title":"Convolutional random walk networks for semantic image segmentation","author":"gedas","year":"0","journal-title":"Proc of CVPR"},{"key":"ref19","first-page":"1","article-title":"Random walks on graphs: A survey","volume":"2","author":"lov\u00e1sz","year":"1993","journal-title":"Combinatorics Paul Erdos Is Eighty"},{"key":"ref28","first-page":"531","article-title":"A comparative study of feature and score normalization for speaker verification","author":"zheng","year":"2006","journal-title":"International Conference on Biometrics"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/ICASSP.2014.6854363"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1006\/dspr.1999.0360"},{"key":"ref3","first-page":"788","article-title":"Front-end factor analysis for speaker verification","volume":"19","author":"najim","year":"2010","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICASSP.2019.8683332"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1016\/j.patrec.2008.02.021"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP.2018.8461375"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref7","article-title":"But system description to voxceleb speaker recognition challenge 2019","author":"zeinali","year":"2019","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TASL.2006.881693"},{"key":"ref9","first-page":"2616","article-title":"Voxceleb: A large-scale speaker identification dataset","author":"nagrani","year":"0","journal-title":"Proc of Interspeech 2017"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref20","article-title":"Speaker attribution with voice profiles by graph-based semi-supervised learning","author":"wang","year":"2021","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1007\/978-3-030-01267-0_30"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.21437\/Interspeech.2021-1209"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref41","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013","journal-title":"ArXiv Preprint"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/CVPR.2018.00241"},{"key":"ref26","first-page":"963","article-title":"Comparison of background normalization methods for text-independent speaker verification","author":"reynolds","year":"0","journal-title":"Proc of Eurospeech"},{"key":"ref25","first-page":"16","article-title":"Unsupervised speaker adaptation based on the cosine similarity for text-independent speaker verification","author":"shum","year":"0","journal-title":"Proc of Odyssey"}],"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\/09687970.pdf?arnumber=9687970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T16:42:14Z","timestamp":1652719334000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9687970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9687970","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}