{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:52:35Z","timestamp":1784645555479,"version":"3.55.0"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/lsp.2020.3044547","type":"journal-article","created":{"date-parts":[[2020,12,14]],"date-time":"2020-12-14T20:51:45Z","timestamp":1607979105000},"page":"121-125","source":"Crossref","is-referenced-by-count":78,"title":["Non-Autoregressive Transformer for Speech Recognition"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6698-1604","authenticated-orcid":false,"given":"Nanxin","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-8631","authenticated-orcid":false,"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9459-8426","authenticated-orcid":false,"given":"Jesus","family":"Villalba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8245-0413","authenticated-orcid":false,"given":"Piotr","family":"Zelasko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4489-5753","authenticated-orcid":false,"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Unsupervised pre-traing for sequence to sequence speech recognition","author":"fan","year":"2019"},{"key":"ref30","article-title":"CAT: CRF-based ASR toolkit","author":"an","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00292"},{"key":"ref11","first-page":"5976","article-title":"Insertion transformer: Flexible sequence generation via insertion operations","author":"stern","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","first-page":"6716","article-title":"Non-monotonic sequential text generation","author":"welleck","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1633"},{"key":"ref14","article-title":"Imputer: Sequence modelling via imputation and dynamic programming","author":"chan","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2086"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref18","first-page":"4171","article-title":"Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Human Lang Technol"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref4","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","article-title":"Corpus of spontaneous japanese: Its design and evaluation","author":"maekawa","year":"0","journal-title":"Proc ISCA & IEEE Workshop Spontaneous Speech Process Recognit"},{"key":"ref3","first-page":"231","article-title":"RWTH STR systems for LibriSpeech: Hybrid vs attention","author":"l\u00fcscher","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref29","article-title":"Byte pair encoding: A text compression scheme that accelerates pattern matching","author":"shibata","year":"1999"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","article-title":"Non-autoregressive neural machine translation","author":"gu","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1149"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref20","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","first-page":"206","article-title":"Exploring neural transducers for end-to-end speech recognition","author":"battenberg","year":"0","journal-title":"Proc IEEE Autom Speech Recognit Understanding Workshop"},{"key":"ref21","first-page":"4601","article-title":"Professor forcing: A new algorithm for training recurrent networks","author":"lamb","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","article-title":"Unified language model pre-training for natural language understanding and generation","author":"dong","year":"2019"},{"key":"ref23","article-title":"Generalized autoregressive pretraining for language understanding","author":"yang","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref25","first-page":"742","article-title":"An efficient algorithm for easy-first non-directional dependency parsing","author":"goldberg","year":"0","journal-title":"Proc Human Lang Technol Annu Conf North Amer Chapter Assoc Comput Linguistics"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/9325893\/09292943.pdf?arnumber=9292943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:50:39Z","timestamp":1652194239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9292943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/lsp.2020.3044547","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}