{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:06:47Z","timestamp":1776888407974,"version":"3.51.2"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003920","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"936-943","source":"Crossref","is-referenced-by-count":27,"title":["Streaming End-to-End Speech Recognition with Joint CTC-Attention Based Models"],"prefix":"10.1109","author":[{"given":"Niko","family":"Moritz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takaaki","family":"Hori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan Le","family":"Roux","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Win-dowed attention mechanisms for speech recognition","author":"zhang","year":"2019","journal-title":"Proc IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404777"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2539499"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2016-759","article-title":"Towards online-recognition with deep bidirectional LSTM acoustic models","author":"zeyer","year":"2016","journal-title":"Proc ISCA Interspeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2837"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2723507"},{"key":"ref18","author":"maas","year":"2014","journal-title":"First-pass large vocabulary continuous speech recognition using bi-directional recurrent dnns"},{"key":"ref19","author":"kudo","year":"2018","journal-title":"SentencePiece A simple and language independent subword tokenizer and detokenizer for neural text processing"},{"key":"ref4","author":"bahdanau","year":"2014","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref27","author":"luong","year":"2015","journal-title":"Effective Approaches to Attention-based Neural Machine Translation"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref6","author":"graves","year":"2012","journal-title":"Sequence transduction with recurrent neural networks"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref8","article-title":"Monotonic chunkwise attention","author":"chiu","year":"2018","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref7","author":"collobert","year":"2016","journal-title":"Wav2letter an end-to-end convnet-based speech recognition system"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref9","article-title":"An online sequence-to-sequence model using partial conditioning","author":"jaitly","year":"2016","journal-title":"Proc NIPS"},{"key":"ref1","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc International Conference on Machine Learning (ICML)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.06.007"},{"key":"ref22","volume":"ldc94s13a","year":"1994","journal-title":"CSR-II (WSJ1) Complete"},{"key":"ref21","article-title":"A comprehensive analysis on attention models","author":"zeyer","year":"2018","journal-title":"Interpretability and Robustness in Audio Speech and Language (IRASL) Workshop NeurIPS"},{"key":"ref24","article-title":"HKUST\/MTS: A very large scale Mandarin telephone speech corpus","volume":"4274","author":"liu","year":"2006","journal-title":"Proc ISCSLP"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref26","article-title":"Ad-vances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM","author":"hori","year":"2017","journal-title":"Proc ISCA Interspeech"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1109\/SLT.2018.8639693","article-title":"End-to-end speech recognition with word-based RNN language models","author":"hori","year":"2018","journal-title":"Proceedings of 2018 IEEE Spoken Language Technology Workshop (SLT)"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"SG, Singapore","start":{"date-parts":[[2019,12,14]]},"end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003920.pdf?arnumber=9003920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:49:25Z","timestamp":1658155765000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/9003920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":27,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/asru46091.2019.9003920","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}