{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:55:59Z","timestamp":1730199359985,"version":"3.28.0"},"reference-count":46,"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\/asru51503.2021.9688243","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:31:00Z","timestamp":1643902260000},"page":"206-213","source":"Crossref","is-referenced-by-count":4,"title":["Duality Temporal-Channel-Frequency Attention Enhanced Speaker Representation Learning"],"prefix":"10.1109","author":[{"given":"Li","family":"Zhang","sequence":"first","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China"}]},{"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref38","first-page":"1","volume":"2","author":"habets","year":"2006","journal-title":"Room impulse response generator"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref30","article-title":"Id r&d system description to voxceleb speaker recognition challenge 2020","author":"torgashov","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref37","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015","journal-title":"Preprint arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2980991"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref34","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-2766-4_5"},{"key":"ref40","article-title":"Speaker augmentation and band-width extension for deep speaker embedding","author":"yamamoto","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1891"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287426"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","first-page":"5359","article-title":"Attention-based models for text-dependent speaker verification","author":"rezaur","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref15","article-title":"BUT system description to voxceleb speaker recognition challenge 2019","author":"zeinali","year":"0","journal-title":"Proc The VoxSRC Workshop"},{"key":"ref16","article-title":"Clova baseline system for the voxceleb speaker recognition challenge 2020","author":"heo","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","article-title":"Multi-stream convolutional neural network with frequency selection for robust speaker verification","author":"yao","year":"2020","journal-title":"IEEEAccess"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1570"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1980"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-49"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1106"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413421"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"iv","DOI":"10.1109\/ICASSP.2002.1004813","article-title":"An overview of automatic speaker recognition technology","volume":"4","author":"reynolds","year":"2002","journal-title":"Proc ICASSP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865704310024"},{"key":"ref46","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","article-title":"BAM: bottleneck attention module","author":"park","year":"0","journal-title":"Proc BMVC"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.01.002"},{"key":"ref22","article-title":"Attention is all you need","volume":"30","author":"ashish","year":"0","journal-title":"Proc NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.58"},{"key":"ref24","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"0","journal-title":"Proc ECCV"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1704"},{"key":"ref44","first-page":"1353","article-title":"The 2016 nist speaker recognition evaluation","author":"sadjadi","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1845"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref25","first-page":"6794","article-title":"Frequency and temporal convolutional attention for text-independent speaker recognition","author":"sarthak","year":"0","journal-title":"Proc ICASSP"}],"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\/09688243.pdf?arnumber=9688243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T16:41:18Z","timestamp":1652719278000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688243\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688243","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}