{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:53:36Z","timestamp":1776884016731,"version":"3.51.2"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434806","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["SV-Mixer: Replacing the Transformer Encoder with Lightweight MLPs for Self-Supervised Model Compresison in Speaker Verification"],"prefix":"10.1109","author":[{"given":"Jungwoo","family":"Heo","sequence":"first","affiliation":[{"name":"University of Seoul,Korea"}]},{"given":"Hyun-Seo","family":"Shin","sequence":"additional","affiliation":[{"name":"University of Seoul,Korea"}]},{"given":"Chan-Yeong","family":"Lim","sequence":"additional","affiliation":[{"name":"University of Seoul,Korea"}]},{"given":"Kyo-Won","family":"Koo","sequence":"additional","affiliation":[{"name":"University of Seoul,Korea"}]},{"given":"Seung-Bin","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Seoul,Korea"}]},{"given":"Jisoo","family":"Son","sequence":"additional","affiliation":[{"name":"University of Seoul,Korea"}]},{"given":"Ha-Jin","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Seoul,Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref2","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2025.101813"},{"key":"ref5","article-title":"Uniwav: Towards unified pre-training for speech representation learning and generation","volume-title":"Proceedings of the 13th International Conference on Learning Representations (ICLR)","author":"Liu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-605"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-486"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2116"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref12","article-title":"Fithubert: Going thinner and deeper for knowledge distillation of speech self-supervised learning","author":"Lee","year":"2022","journal-title":"arXiv preprint arXiv:2207.00555"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10269"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447928"},{"key":"ref15","first-page":"21 256","article-title":"Parp: Prune, adjust and re-prune for self-supervised speech recognition","volume":"34","author":"Lai","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref17","article-title":"Rethinking attention with performers","volume-title":"International Conference on Learning Representations","author":"Choromanski"},{"key":"ref18","article-title":"Reformer: The efficient transformer","volume-title":"International Conference on Learning Representations","author":"Kitaev"},{"key":"ref19","first-page":"24261","article-title":"Mlp-mixer: An all-mlp architecture for vision","volume":"34","author":"Tolstikhin","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3303397"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747172"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1213"},{"key":"ref24","first-page":"9204","article-title":"Pay attention to mlps","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.14778\/3712221.3712243"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746257"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"issue":"4","key":"ref31","doi-asserted-by":"crossref","first-page":"819","DOI":"10.31577\/cai_2024_4_819","article-title":"Multi-stream convolutional neural network with frequency selection for robust speaker verification","volume":"43","author":"Yao","year":"2024","journal-title":"Computing and Informatics"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref34","article-title":"MUSAN: A Music, Speech, and Noise Corpus","author":"Snyder","year":"2015","journal-title":"arXiv:1510.08484v1"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3444456"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445987"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-27"},{"key":"ref40","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv:1711.05101"},{"key":"ref41","article-title":"Sphereface2: Binary classification is all you need for deep face recognition","volume-title":"International Conference on Learning Representations","author":"Wen"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-360"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434806.pdf?arnumber=11434806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:58Z","timestamp":1775192398000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434806","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}