{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:33:47Z","timestamp":1776890027109,"version":"3.51.2"},"reference-count":46,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383517","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"22-29","source":"Crossref","is-referenced-by-count":29,"title":["Streaming Transformer Asr With Blockwise Synchronous Beam Search"],"prefix":"10.1109","author":[{"given":"Emiru","family":"Tsunoo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yosuke","family":"Kashiwagi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054250"},{"key":"ref33","first-page":"947","article-title":"Spontaneous speech corpus of Japanese","author":"maekawa","year":"2000","journal-title":"Proc Int Conference on Language Resources and Evaluation (LREC)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/11939993_73"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2860"},{"key":"ref36","article-title":"Generating long sequences with sparse transformers","author":"child","year":"2019"},{"key":"ref35","first-page":"5067","article-title":"An online sequence-to-sequence model using partial conditioning","author":"jaitly","year":"2016","journal-title":"Proc of NIPS"},{"key":"ref34","first-page":"7884","article-title":"Synchronous transformers for end-to-end speech recognition","author":"tian","year":"2020","journal-title":"Proc of ICASSP"},{"key":"ref10","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc of NeurIPS"},{"key":"ref40","first-page":"2207","article-title":"ESPnet: End-to-end speech processing toolkit","author":"watanabe","year":"2019","journal-title":"Proc of Interspeech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1910"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682539"},{"key":"ref13","first-page":"7095","article-title":"The Speech Transformer for large-scale Mandarin Chinese speech recognition","author":"zhao","year":"2019","journal-title":"Proc of ICASSP"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462497"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682954"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053165"},{"key":"ref28","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref4","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc of NIPS"},{"key":"ref27","article-title":"Learning small-size DNN with output-distribution-based criteria","author":"li","year":"2014","journal-title":"Proc of 15th Annual Conference of the International Speech Communication Association"},{"key":"ref3","first-page":"173","article-title":"Deep Speech 2: End-to-end speech recognition in English and Mandarin","volume":"48","author":"amodei","year":"2016","journal-title":"Proc of 33rd International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953072"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref9","first-page":"193","article-title":"Exploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer","author":"rao","year":"2017","journal-title":"Proc IEEE ASRU Workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053040"},{"key":"ref22","article-title":"Monotonic chunkwise attention","author":"chiu","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003749"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004027"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2218"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref26","first-page":"6064","article-title":"Minimum latency training strategies for streaming sequence-to-sequence ASR","author":"inaguma","year":"2020","journal-title":"Proc of ICASSP"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref25","article-title":"Towards online end-to-end transformer automatic speech recognition","author":"tsunoo","year":"2019"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383517.pdf?arnumber=9383517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T21:59:51Z","timestamp":1620165591000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383517\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383517","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}