{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T05:36:37Z","timestamp":1774935397231,"version":"3.50.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3471183","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:29:19Z","timestamp":1727717359000},"page":"144684-144697","source":"Crossref","is-referenced-by-count":1,"title":["Ubranch Conformer: Integrating Up-Down Sampling and Branch Attention for Speech Recognition"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2008-9181","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China"}]},{"given":"Feng","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China"}]},{"given":"Mingke","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China"}]},{"given":"Yucheng","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3328283"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10073-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3212767"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref8","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref9","first-page":"1","article-title":"Understanding the role of self attention for efficient speech recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Shim"},{"key":"ref10","first-page":"17627","article-title":"Branchformer: Parallel mlp-attention architectures to capture local and global context for speech recognition and understanding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3218684"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-1446"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383532"},{"key":"ref15","article-title":"Citrinet: Closing the gap between non-autoregressive and autoregressive end-to-end models for automatic speech recognition","author":"Majumdar","year":"2021","journal-title":"arXiv:2104.01721"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3112535"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-893"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095469"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022656"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687874"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095430"},{"key":"ref24","first-page":"9361","article-title":"Squeezeformer: An efficient transformer for automatic speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Kim"},{"key":"ref25","article-title":"Zipformer: A faster and better encoder for automatic speech recognition","author":"Yao","year":"2023","journal-title":"arXiv:2310.11230"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446861"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref31","article-title":"Fastformer: Additive attention can be all you need","author":"Wu","year":"2021","journal-title":"arXiv:2108.09084"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3144163"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.06.111"},{"key":"ref34","article-title":"Lite transformer with long-short range attention","author":"Wu","year":"2020","journal-title":"arXiv:2004.11886"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-3481-2_55"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053573"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10340"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-483"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-994"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3403761"},{"key":"ref50","article-title":"Towards decoupling frontend enhancement and backend recognition in monaural robust ASR","author":"Yang","year":"2024","journal-title":"arXiv:2403.06387"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-024-10288-y"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10700716.pdf?arnumber=10700716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,12]],"date-time":"2024-10-12T04:30:44Z","timestamp":1728707444000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10700716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3471183","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}