{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T21:47:31Z","timestamp":1753739251598},"reference-count":31,"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\/icassp40776.2020.9054663","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7079-7083","source":"Crossref","is-referenced-by-count":17,"title":["Exploring Pre-Training with Alignments for RNN Transducer Based End-to-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Hu","family":"Hu","sequence":"first","affiliation":[]},{"given":"Rui","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref31","article-title":"Neural machine translation of rare words with subword units","author":"sennrich","year":"2015","journal-title":"arXiv preprint arXiv 1508 07909"},{"key":"ref30","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv preprint arXiv 1609 04802"},{"key":"ref10","article-title":"Towards Discriminatively-trained HMM-based End-to-end models for Automatic Speech Recognition","author":"hadian","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462366"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref14","first-page":"1764","article-title":"Towards End-to-End Speech Recognition with Recurrent Neural Networks","author":"graves","year":"2014","journal-title":"PMLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2933325"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref17","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"bahdanau","year":"2015","journal-title":"ICLRE"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref19","article-title":"Attention-Based Models for Speech Recognition","author":"chorowski","year":"2015","journal-title":"NIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref27","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"939","DOI":"10.21437\/Interspeech.2017-233","article-title":"A Comparison of Sequence-to-Sequence Models for Speech Recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref29","article-title":"Exploring rnn-transducer for chinese speech recognition","author":"wang","year":"2018","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268937"},{"key":"ref7","article-title":"State-of-theart speech recognition with sequence-to-sequence models","author":"chiu","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-169","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1705","article-title":"Recurrent neural aligner: An encoder-decoder neural network model for sequence to sequence mapping","author":"sak","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","article-title":"Sequence Transduction with Recurrent Neural Networks","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003906"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref23","article-title":"Monotonic chunkwise attention","author":"chiu","year":"2017","journal-title":"arXiv preprint arXiv 1712 05382"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268937"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","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\/09054663.pdf?arnumber=9054663","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:28:03Z","timestamp":1696015683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054663\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054663","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}