{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:19:11Z","timestamp":1761581951878},"reference-count":39,"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\/icassp40776.2020.9054098","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6064-6068","source":"Crossref","is-referenced-by-count":20,"title":["Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR"],"prefix":"10.1109","author":[{"given":"Hirofumi","family":"Inaguma","sequence":"first","affiliation":[]},{"given":"Yashesh","family":"Gaur","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yifan","family":"Gong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"959","article-title":"Direct acoustics-to-word models for English conversational speech recognition","author":"audhkhasi","year":"2017","journal-title":"Proceedings of INTER-SPEECH"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1118"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"article-title":"Layer normalization","year":"2016","author":"ba","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1030"},{"key":"ref36","first-page":"369","article-title":"A comparison of techniques for language model integration in encoder-decoder speech recognition","author":"toshniwal","year":"2018","journal-title":"Proceedings of SLT"},{"key":"ref35","first-page":"5824","article-title":"An analysis of incorporating an external language model into a sequence-to-sequence model","author":"kannan","year":"2017","journal-title":"Proceedings of ICASSP"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-334"},{"key":"ref11","first-page":"431","article-title":"Local monotonic attention mechanism for end-to-end speech and language processing","author":"tjandra","year":"2017","journal-title":"Proceedings of IJCNLP"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"3692","DOI":"10.21437\/Interspeech.2017-751","article-title":"Gaussian prediction based attention for online end-to-end speech recognition","author":"hou","year":"2017","journal-title":"Proceedings of Interspeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2879"},{"article-title":"A neural transducer","year":"2015","author":"jaitly","key":"ref14"},{"key":"ref15","first-page":"2837","article-title":"Online and linear-time attention by enforcing monotonic alignments","author":"raffel","year":"2017","journal-title":"Proceedings of ICML"},{"key":"ref16","article-title":"Monotonic chunkwise attention","author":"chiu","year":"2018","journal-title":"Proceedings of ICL"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682500"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"article-title":"CIF: Continuous integrate-and-fire for end-to-end speech recognition","year":"2019","author":"dong","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1126"},{"key":"ref4","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":"Proceedings of Interspeech"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1452"},{"key":"ref3","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"year":"2014","author":"chung","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268937"},{"article-title":"Sequence transduction with recurrent neural networks","year":"2012","author":"graves","key":"ref8"},{"key":"ref7","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proceedings of ICML"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004027"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2218"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003936"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1049"},{"key":"ref25","first-page":"604","article-title":"Acoustic modelling with CD-CTC-sMBR LSTM RNNs","author":"sak","year":"2015","journal-title":"Proceedings of ASRU"}],"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\/09054098.pdf?arnumber=9054098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:26:08Z","timestamp":1656375968000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054098\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054098","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}