{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:32:37Z","timestamp":1776889957035,"version":"3.51.2"},"reference-count":26,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2020AAA0140003"],"award-info":[{"award-number":["2020AAA0140003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61901473"],"award-info":[{"award-number":["61901473"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61831022"],"award-info":[{"award-number":["61831022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research Project","award":["2019KD0AD01"],"award-info":[{"award-number":["2019KD0AD01"]}]},{"name":"Inria-CAS Joint Research Project","award":["173211KYSB20190049"],"award-info":[{"award-number":["173211KYSB20190049"]}]},{"name":"Huawei Noah’s Ark Lab"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/lsp.2022.3152128","type":"journal-article","created":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T20:28:10Z","timestamp":1645043290000},"page":"762-766","source":"Crossref","is-referenced-by-count":25,"title":["Hybrid Autoregressive and Non-Autoregressive Transformer Models for Speech Recognition"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0469-3049","authenticated-orcid":false,"given":"Zhengkun","family":"Tian","sequence":"first","affiliation":[{"name":"NLPR Lab, CASIA, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-4618","authenticated-orcid":false,"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[{"name":"NLPR Lab, CASIA, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"NLPR Lab, CASIA, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1094-887X","authenticated-orcid":false,"given":"Shuai","family":"Zhang","sequence":"additional","affiliation":[{"name":"NLPR Lab, CASIA, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[{"name":"NLPR Lab, CASIA, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"C","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref3","first-page":"4835","article-title":"Joint CTC-attention based end-to-end speech recognition using multi-task learning","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process.","author":"Suyoun","year":"2017"},{"key":"ref4","first-page":"5884","article-title":"Speech-transformer: A no-recurrence sequence-to-sequence model for speech recognition","volume-title":"Proc. IEEE Int. Conf. Acoust., Speech Signal Process.","author":"Linhao","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref9","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"Yeh","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3044547"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2404"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414198"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414694"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2086"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1600"},{"key":"ref16","first-page":"1","article-title":"Dual-mode ASR: Unify and improve streaming ASR with full-context modeling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref19","first-page":"454","article-title":"One in a hundred: Selecting the best predicted sequence from numerous candidates for speech recognition","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. (APSIPA ASC)","author":"Tian","year":"2021"},{"key":"ref20","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682586"},{"key":"ref22","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref23","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Dauphin","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1619"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3044547"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/9686799\/09714840.pdf?arnumber=9714840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:09:08Z","timestamp":1705532948000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9714840\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/lsp.2022.3152128","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}