{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:35Z","timestamp":1774420115643,"version":"3.50.1"},"reference-count":24,"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\/icassp49660.2025.10887794","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":1,"title":["A Modular-based Strategy for Mitigating Gradient Conflicts in Simultaneous Speech Translation"],"prefix":"10.1109","author":[{"given":"Xiaoqian","family":"Liu","sequence":"first","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]},{"given":"Yangfan","family":"Du","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]},{"given":"Jianjin","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]},{"given":"Yuan","family":"Ge","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]},{"given":"Chen","family":"Xu","sequence":"additional","affiliation":[{"name":"Harbin Engineering University,College of Computer Science and Technology,Harbin,China"}]},{"given":"Tong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]},{"given":"Guocheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]},{"given":"Jingbo","family":"Zhu","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-008-9047-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2090"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/900"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758176"},{"key":"ref5","first-page":"6796","article-title":"Recent advances in direct speech-to-text translation","volume-title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI 2023, 19th-25th August 2023, Macao, SAR, China","author":"Xu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.204"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.744"},{"key":"ref8","first-page":"803","article-title":"Multiple dimension levenshtein edit distance calculations for evaluating automatic speech recognition systems during simultaneous speech","volume-title":"Proceedings of the Fifth International Conference on Language Resources and Evaluation, LREC 2006, Genoa, Italy, May 22-28, 2006","author":"Fiscus"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2024-1814","article-title":"Simul-whisper: Attention-guided streaming whisper with truncation detection","volume-title":"CoRR","author":"Wang","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1289"},{"key":"ref11","article-title":"Gradient surgery for multi-task learning","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020","author":"Yu"},{"key":"ref12","article-title":"Don\u2019t decay the learning rate, increase the batch size","volume-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings","author":"Smith"},{"key":"ref13","article-title":"On the pareto front of multilingual neural machine translation","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023","author":"Chen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1008"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6452"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.105"},{"key":"ref17","first-page":"1484","article-title":"Learning multiple tasks using shared hypotheses","volume-title":"Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012","author":"Crammer"},{"key":"ref18","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, NAACLHLT 2019, Minneapolis, MN, USA, June 2-7, 2019","volume":"1","author":"Gangi"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-demo.6"},{"key":"ref21","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020","author":"Baevski"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.485"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.19"},{"key":"ref24","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\/10887794.pdf?arnumber=10887794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:29Z","timestamp":1774416389000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887794\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887794","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}