{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:29:13Z","timestamp":1759332553854,"version":"3.37.3"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095433","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":9,"title":["Towards A Unified Conformer Structure: from ASR to ASV Task"],"prefix":"10.1109","author":[{"given":"Dexin","family":"Liao","sequence":"first","affiliation":[{"name":"Xiamen University,School of Informatics,China"}]},{"given":"Tao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Xiamen Talentedsoft Co., Ltd.,China"}]},{"given":"Feng","family":"Wang","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Informatics,China"}]},{"given":"Lin","family":"Li","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Electronic Science and Engineering,China"}]},{"given":"Qingyang","family":"Hong","sequence":"additional","affiliation":[{"name":"Xiamen University,School of Informatics,China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3036"},{"journal-title":"MUSAN A Music Speech and Noise Corpus","year":"2015","author":"snyder","key":"ref35"},{"journal-title":"Mfa-conformer Multi-scale feature aggregation conformer for automatic speaker verification","year":"2022","author":"zhang","key":"ref12"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2161"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414676"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054760"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"journal-title":"Fantastic generalization measures and where to find them","year":"2019","author":"jiang","key":"ref31"},{"journal-title":"On large-batch training for deep learning Generalization gap and sharp minima","year":"2016","author":"keskar","key":"ref30"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"year":"0","key":"ref33"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746050"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"journal-title":"But system description to voxceleb speaker recognition challenge 2019","year":"2019","author":"zeinali","key":"ref2"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-355"},{"year":"0","key":"ref39"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-807"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-803","article-title":"Analysis of score normalization in multilingual speaker recognition","author":"matejka","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref19","article-title":"Olr 2021 challenge: Datasets, rules and baselines","author":"wang","year":"2021","journal-title":"Proc APSIPA ASC"},{"journal-title":"Wenet 2 0 More productive end-to-end speech recognition toolkit","year":"2022","author":"zhang","key":"ref18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"journal-title":"Roformer Enhanced transformer with rotary position embedding","year":"2022","author":"su","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.01.002"},{"journal-title":"Overcoming a theoretical limitation of self-attention","year":"2022","author":"chiang","key":"ref20"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-950","article-title":"Voxceleb: a large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref21","article-title":"Sharpness-aware minimization for efficiently improving generalization","author":"foret","year":"2021","journal-title":"Proc ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"article-title":"Scale operation of attention from entropy invariance","year":"2022","author":"su","key":"ref29"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc ICLR"},{"journal-title":"BERT Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1446"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383531"},{"key":"ref6","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"journal-title":"The speakin system for voxceleb speaker recognition challange 2021","year":"2021","author":"zhao","key":"ref5"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095433.pdf?arnumber=10095433","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:57:51Z","timestamp":1700506671000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095433\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095433","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}