{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:56:38Z","timestamp":1774367798302,"version":"3.50.1"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021YFE0205400"],"award-info":[{"award-number":["2021YFE0205400"]}]},{"name":"National Key Research and Development Program of China","award":["2021YFE0100100"],"award-info":[{"award-number":["2021YFE0100100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1909209"],"award-info":[{"award-number":["U1909209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"R&D Program of Zhejiang","award":["2022C03117"],"award-info":[{"award-number":["2022C03117"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/lsp.2023.3328238","type":"journal-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T18:12:42Z","timestamp":1698430362000},"page":"1592-1596","source":"Crossref","is-referenced-by-count":4,"title":["A Transformer-Based End-to-End Automatic Speech Recognition Algorithm"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3205-9931","authenticated-orcid":false,"given":"Fang","family":"Dong","sequence":"first","affiliation":[{"name":"School of Information and Electrical Engineering, Hangzhou City University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7310-5608","authenticated-orcid":false,"given":"Yiyang","family":"Qian","sequence":"additional","affiliation":[{"name":"Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4498-4326","authenticated-orcid":false,"given":"Tianlei","family":"Wang","sequence":"additional","affiliation":[{"name":"Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7485-5745","authenticated-orcid":false,"given":"Peng","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang Baiying Technology Ltd. Company, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6480-5794","authenticated-orcid":false,"given":"Jiuwen","family":"Cao","sequence":"additional","affiliation":[{"name":"Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref4","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1910"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref10","article-title":"Aishell-2: Transforming mandarin asr research into industrial scale","author":"Du","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66429-3_51"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-40"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053126"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1209"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747714"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747101"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2986"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3154241"},{"key":"ref20","article-title":"Fast and robust unsupervised contextual biasing for speech recognition","author":"Kang","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415054"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1938"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1983"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref27","article-title":"First-pass large vocabulary continuous speech recognition using Bi-directional recurrent DNNs","author":"Hannun","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/1073336.1073340"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053205"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref32","first-page":"1","article-title":"Adam: A. method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref34","first-page":"1","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bengio","year":"2015"},{"key":"ref35","article-title":"Googles neural machine translation system: Bridging the gap between human and machine translation","author":"Wu","year":"2016"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/10036333\/10298618.pdf?arnumber=10298618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T10:35:32Z","timestamp":1710412532000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10298618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/lsp.2023.3328238","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}