{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:30:39Z","timestamp":1776886239373,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746903","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"6527-6531","source":"Crossref","is-referenced-by-count":10,"title":["Non-Autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Chuan-Fei","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Science and Technology Beijing,School of Automation and Electrical Engineering,Beijing,China,100083"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing,School of Automation and Electrical Engineering,Beijing,China,100083"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian-Hao","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing,USTB-EEasyTech Joint Lab of Artificial Intelligence,Beijing,China,100083"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song-Lu","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing,USTB-EEasyTech Joint Lab of Artificial Intelligence,Beijing,China,100083"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing,USTB-EEasyTech Joint Lab of Artificial Intelligence,Beijing,China,100083"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu-Cheng","family":"Yin","sequence":"additional","affiliation":[{"name":"University of Science and Technology Beijing,USTB-EEasyTech Joint Lab of Artificial Intelligence,Beijing,China,100083"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","first-page":"1408","article-title":"Improving transformer-based end-to-end speech recognition with connectionist temporal classification and language model integration","author":"karita","year":"2020","journal-title":"InterSpeech"},{"key":"ref10","first-page":"5889","article-title":"CASS-NAT: CTC alignment-based single step non-autoregressive transformer for speech recognition","author":"fan","year":"2021","journal-title":"ICASSP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1600"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414694"},{"key":"ref14","article-title":"TSNAT: two-step non-autoregressvie transformer models for speech recognition","author":"tian","year":"2021"},{"key":"ref15","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2677"},{"key":"ref17","article-title":"U2++: Unified two-pass bidirectional end-to-end model for speech recognition","author":"wu","year":"2021"},{"key":"ref18","first-page":"5144","article-title":"Non-autoregressive machine translation with disentangled contexts transformer","author":"kasai","year":"2020","journal-title":"ICML"},{"key":"ref19","article-title":"layer normalization","author":"ba","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1619"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054715"},{"key":"ref27","first-page":"3586","article-title":"Audio augmentation for speech recognition","author":"ko","year":"2015","journal-title":"InterSpeech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref6","article-title":"Non-autoregressive neural machine translation","author":"gu","year":"2018","journal-title":"ICLRE"},{"key":"ref29","article-title":"Listen and fill in the missing letters: Non-autoregressive transformer for speech recognition","author":"chen","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1149"},{"key":"ref7","first-page":"3515","article-title":"Aligned cross entropy for non-autoregressive machine translation","author":"ghazvininejad","year":"2020","journal-title":"ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1281"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2086"},{"key":"ref1","first-page":"5884","article-title":"Speech-Transformer: a no-recurrence sequence-to-sequence model for speech recognition","author":"dong","year":"2018","journal-title":"ICASSP"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref24","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746903.pdf?arnumber=9746903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:09:17Z","timestamp":1660579757000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746903","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}