{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T01:09:25Z","timestamp":1760404165457,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003826","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"718-725","source":"Crossref","is-referenced-by-count":36,"title":["CNN with Phonetic Attention for Text-Independent Speaker Verification"],"prefix":"10.1109","author":[{"given":"Tianyan","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Yong","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref32","first-page":"2365","article-title":"Restructuring of deep neural network acoustic models with singular value decomposition","author":"xue","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683783"},{"key":"ref30","first-page":"338","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"hasim","year":"2014","journal-title":"TERSPEECH"},{"key":"ref34","article-title":"Unified hypersphere embedding for speaker recognition","volume":"abs 1807 8312","author":"hajibabaei","year":"2018","journal-title":"CoRR"},{"journal-title":"Deep speaker an end-to-end neural speaker embedding system","year":"2017","author":"li","key":"ref10"},{"key":"ref11","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":"InterSpeech"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref14","article-title":"Exploring the encoding layer and loss function in end-to-end speaker and language recognition system","volume":"abs 1804 5160","author":"cai","year":"2018","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","first-page":"1695","article-title":"A novel scheme for speaker recognition using a phonetically-aware deep neural network","author":"lei","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref17","article-title":"Improving speaker recognition performance in the domain adaptation challenge using deep neural networks","author":"garcia-romero","year":"2015","journal-title":"Spoken Language Technology Workshop"},{"key":"ref18","first-page":"92","article-title":"Time delay deep neural network-based universal background models for speaker recognition","author":"snyder","year":"2016","journal-title":"Proc Automatic Speech Recognition and Understanding"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2015.2420092"},{"key":"ref28","article-title":"L2-constrained softmax loss for discriminative face verification","volume":"abs 1703 9507","author":"rajeev","year":"2017","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"505","DOI":"10.21437\/Interspeech.2011-142","article-title":"Towards fully bayesian speaker recognition: Integrating out the between-speaker covariance","author":"villalba","year":"2011","journal-title":"Proceedings of INTERSPEECH 2011 International Speech Communication Association"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"ref6","first-page":"999","article-title":"Deep neural network embed-dings for text-independent speaker verification","author":"snyder","year":"2017","journal-title":"TERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"249","DOI":"10.21437\/Interspeech.2011-53","article-title":"Anal-ysis of i-vector length normalization in speaker recognition systems","author":"garcia-romero","year":"2011","journal-title":"Proceedings of INTERSPEECH 2011 International Speech Communication Association"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref7","first-page":"4052","article-title":"Deep neural networks for small footprint text-dependent speaker verification","author":"variani","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref2","first-page":"788","article-title":"Front-end factor analysis for speaker verification","volume":"19","author":"najim","year":"2010","journal-title":"IEEE Transactionson Audio Speech and Language Processing"},{"key":"ref9","first-page":"5329","article-title":"X-vectors: Robust DNN embeddings for speaker recognition","author":"snyder","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref1","first-page":"iv-4072","article-title":"An overview of automatic speaker recognition technology","author":"reynolds","year":"2011","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1804"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846261"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1226"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1158"},{"key":"ref23","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref25","first-page":"5359","article-title":"Attention-based models for text-dependent speaker verification","author":"rezaur","year":"2018","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2019,12,14]]},"location":"SG, Singapore","end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003826.pdf?arnumber=9003826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T08:49:55Z","timestamp":1695804595000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003826\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003826","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}