{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T11:06:27Z","timestamp":1750331187477,"version":"3.37.3"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100015956","name":"Key Research and Development Program of Guangdong Province","doi-asserted-by":"publisher","award":["No.2021B0101400003"],"award-info":[{"award-number":["No.2021B0101400003"]}],"id":[{"id":"10.13039\/501100015956","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9892002","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-7","source":"Crossref","is-referenced-by-count":5,"title":["DT-SV: A Transformer-based Time-domain Approach for Speaker Verification"],"prefix":"10.1109","author":[{"given":"Nan","family":"Zhang","sequence":"first","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhou","family":"Hong","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chendong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyang","family":"Qu","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Xiao","sequence":"additional","affiliation":[{"name":"Ping An Technology (Shenzhen) Co., Ltd.,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2016"},{"key":"ref38","article-title":"Raw-x-vector: Multi-scale time domain speaker embedding network","author":"zhu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683445"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1287"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1011"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414261"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414877"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413737"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2039"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-620"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362054"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","article-title":"Front-end factor analysis for speaker verification","volume":"19","author":"dehak","year":"2010","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414765"},{"key":"ref29","first-page":"2616","article-title":"VoxCeleb: A large-scale speaker identification dataset","author":"nagrani","year":"0","journal-title":"2017 Conference of the International Speech Communication Association (Interspeech)"},{"key":"ref5","first-page":"6179","article-title":"Small foot-print text-independent speaker verification for embedded systems","author":"balian","year":"0","journal-title":"2021 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref8","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"3rd International Conference on Learning Representations ICLR 2015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414859"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533666"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3057"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref22","first-page":"1689","article-title":"Speaker verification system based on deformable cnn and time-frequency attention","author":"zhang","year":"0","journal-title":"2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3134566"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_41"},{"key":"ref23","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies NAACL-HLT"},{"key":"ref26","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"9th International Conference on Learning Representations ICLR 2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2210"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09892002.pdf?arnumber=9892002","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:56:33Z","timestamp":1667516193000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9892002\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9892002","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}