{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T21:32:34Z","timestamp":1781818354013,"version":"3.54.5"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004921","name":"Shanghai Jiao Tong University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004921","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746050","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6727-6731","source":"Crossref","is-referenced-by-count":21,"title":["Local Information Modeling with Self-Attention for Speaker Verification"],"prefix":"10.1109","author":[{"given":"Bing","family":"Han","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref11","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1075"},{"key":"ref13","first-page":"6888","article-title":"Towards data selection on tts data for children’s speech recognition","author":"wang","year":"2021","journal-title":"Proc IEEE ICASSP"},{"key":"ref14","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref15","article-title":"S-vectors: Speaker embeddings based on transformer’s encoder for text-independent speaker verification","author":"katta","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1446"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref18","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016489"},{"key":"ref4","article-title":"The xx205 system for the voxceleb speaker recognition challenge 2020","author":"xiang","year":"2020"},{"key":"ref3","article-title":"But system description to vox-celeb speaker recognition challenge 2019","author":"zeinali","year":"2019"},{"key":"ref6","first-page":"531","article-title":"Probabilistic linear discriminant analysis","author":"ioffe","year":"2006","journal-title":"European Conference on Computer Vision"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-29"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2136"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.07.003"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref21","article-title":"Disan: Directional self-attention network for rnn\/cnn-free language understanding","volume":"32","author":"shen","year":"2018","journal-title":"Proc AAAI"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2980991"},{"key":"ref23","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref25","article-title":"Mu-san: A music, speech, and noise corpus","author":"snyder","year":"2015"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746050.pdf?arnumber=9746050","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:08:19Z","timestamp":1660594099000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746050\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746050","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}