{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T11:15:08Z","timestamp":1760267708695},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054260","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"source":"Crossref","is-referenced-by-count":39,"title":["Synchronous Transformers for end-to-end Speech Recognition"],"prefix":"10.1109","author":[{"given":"Zhengkun","family":"Tian","sequence":"first","affiliation":[]},{"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[]},{"given":"Ye","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[]},{"given":"Shuai","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"ref11","article-title":"A neural transducer","author":"jaitly","year":"2015"},{"key":"ref12","first-page":"5067","article-title":"An on-line sequence-to-sequence model using partial conditioning","author":"jaitly","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462366"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"6645","DOI":"10.1109\/ICASSP.2013.6638947","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"2013","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref16","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref19","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"0"},{"key":"ref4","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref8","article-title":"Monotonic chunkwise attention","author":"chiu","year":"2017"},{"key":"ref7","article-title":"Local monotonic attention mechanism for end-to-end speech and language processing","author":"tjandra","year":"2017"},{"key":"ref2","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682490"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054260.pdf?arnumber=9054260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:15:47Z","timestamp":1656375347000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054260\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054260","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}