{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T14:57:12Z","timestamp":1785596232848,"version":"3.56.0"},"reference-count":36,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Foundation","award":["2021B1515120025"],"award-info":[{"award-number":["2021B1515120025"]}]},{"name":"Research Foundation","award":["2021KSYS008"],"award-info":[{"award-number":["2021KSYS008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/lsp.2024.3358754","type":"journal-article","created":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T18:42:13Z","timestamp":1706208133000},"page":"471-475","source":"Crossref","is-referenced-by-count":12,"title":["ESAformer: Enhanced Self-Attention for Automatic Speech Recognition"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3723-279X","authenticated-orcid":false,"given":"Junhua","family":"Li","sequence":"first","affiliation":[{"name":"Foshan University, Foshan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7429-9357","authenticated-orcid":false,"given":"Zhikui","family":"Duan","sequence":"additional","affiliation":[{"name":"Foshan University, Foshan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8746-1787","authenticated-orcid":false,"given":"Shiren","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinmei","family":"Yu","sequence":"additional","affiliation":[{"name":"Foshan University, Foshan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6755-242X","authenticated-orcid":false,"given":"Guangguang","family":"Yang","sequence":"additional","affiliation":[{"name":"Foshan University, Foshan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.19"},{"key":"ref3","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref4","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visio linguistic representations for vision-and-language tasks","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3176486"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3241558"},{"key":"ref7","article-title":"Lite transformer with long-short range attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3180668"},{"key":"ref12","first-page":"10353","article-title":"HorNet: Efficient high-order spatial interactions with recursive gated convolutions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rao","year":"2022"},{"key":"ref13","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dauphin","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3044547"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref16","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","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.81"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/11939993_73"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2022.0029"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054260"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1600"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1619"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413429"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682954"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682539"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1086"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472152"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053954"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10380231\/10414120.pdf?arnumber=10414120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T20:41:25Z","timestamp":1707252085000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10414120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/lsp.2024.3358754","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}