{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:18:59Z","timestamp":1774419539408,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890091","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing Speech Multi-View Feature Fusion through Conditional Computation"],"prefix":"10.1109","author":[{"given":"Weiqiao","family":"Shan","sequence":"first","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Han","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bei","family":"Li","sequence":"additional","affiliation":[{"name":"Meituan,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Huawei Translation Services Center,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuang","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Translation Services Center,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Translation Services Center,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[{"name":"Huawei Translation Services Center,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingbo","family":"Zhu","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/2000000001"},{"key":"ref2","first-page":"178","article-title":"Learning robust features using deep learning for automatic seizure detection","volume-title":"Machine learning for healthcare conference","author":"Thodoroff"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472621"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref5","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"International Conference on Machine Learning","author":"Baevski"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref8","first-page":"3287","article-title":"Exploration on HuBERT with Multiple Resolutions","volume-title":"Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH","volume":"2023","author":"Shi"},{"key":"ref9","article-title":"Multi-resolution HuBERT: Multi-resolution speech self-supervised learning with masked unit prediction","author":"Shi","year":"2023"},{"key":"ref10","article-title":"Unit-speech: Speaker-adaptive speech synthesis with untranscribed data","author":"Kim","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1055"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17210"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.090"},{"key":"ref14","article-title":"The platonic representation hypothesis","author":"Huh","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10796"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2023.102262"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39593-2_1"},{"key":"ref18","article-title":"Depth-adaptive transformer","author":"Elbayad","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.681"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref21","article-title":"Sparsely activated mixture-of-experts are robust multi-task learners","author":"Gupta","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.204"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447494"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412236"},{"key":"ref26","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"2012","article-title":"Must-c: a multilingual speech translation corpus","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Di Gangi"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.115"},{"key":"ref30","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890091.pdf?arnumber=10890091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:24Z","timestamp":1774416204000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890091\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890091","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}