{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:33Z","timestamp":1760245053182},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054448","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"7579-7583","source":"Crossref","is-referenced-by-count":9,"title":["H-Vectors: Utterance-Level Speaker Embedding Using a Hierarchical Attention Model"],"prefix":"10.1109","author":[{"given":"Yanpei","family":"Shi","sequence":"first","affiliation":[]},{"given":"Qiang","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Hain","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1685"},{"key":"ref12","first-page":"2579","article-title":"Visualizing data using t-sne","author":"maaten","year":"2008","journal-title":"JMLR"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Odyssey.2018-46","article-title":"How to train your speaker embeddings extractor","author":"mclaren","year":"2018","journal-title":"Odyssey"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"378","DOI":"10.21437\/Odyssey.2018-53","article-title":"On deep speaker embeddings for text-independent speaker recognition","author":"novoselov","year":"2018","journal-title":"Proc Odyssey 2018 The Speaker and Language Recognition Workshop"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1799"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC.2017.7868454"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1044"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-59"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-620","article-title":"Deep neural network embeddings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"InterSpeech"},{"journal-title":"Switchboard Cellular Part 1 Transcribed Audio","year":"2001","author":"graff","key":"ref4"},{"key":"ref3","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"NIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2015.7230492"},{"key":"ref5","first-page":"788","article-title":"Front-end factor analysis for speaker verification","author":"dehak","year":"2010","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"journal-title":"2008 NIST Speaker Recognition Evaluation Training Set Part 2 LDC2011S07","year":"2011","author":"group","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2108"},{"key":"ref9","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"ICML"},{"journal-title":"Call-home american english speech","year":"2001","author":"canavan","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref21","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","author":"srivastava","year":"2014","journal-title":"JMLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639586"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054448.pdf?arnumber=9054448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:26:08Z","timestamp":1656361568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054448","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}