{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:22:43Z","timestamp":1776889363349,"version":"3.51.2"},"reference-count":41,"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:\/\/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:\/\/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:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003749","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"427-433","source":"Crossref","is-referenced-by-count":38,"title":["Transformer ASR with Contextual Block Processing"],"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":"Toshiyuki","family":"Kumakura","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","first-page":"2207","article-title":"ESPnet: End-to-end speech processing toolkit","author":"watanabe","year":"2019","journal-title":"Proc of Interspeech"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref33","author":"zihang","year":"2019","journal-title":"Transformer-xl Attentive language models beyond a fixed-length context"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-751"},{"key":"ref30","author":"chiu","year":"2017","journal-title":"Monotonic chunkwise attention"},{"key":"ref37","first-page":"1","article-title":"AIShell-1: An open-source Mandarin speech corpus and a speech recognition baseline","author":"na","year":"2017","journal-title":"Oriental COCOSDA"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref35","first-page":"4790","article-title":"Conditional image generation with PixelCNN decoders","author":"van den oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref34","author":"child","year":"2019","journal-title":"Generating long sequences with sparse transformers"},{"key":"ref10","first-page":"5060","article-title":"On training the recurrent neural network encoder-decoder for large vocabu-1ary end-to-end speech recognition","author":"lu","year":"2016","journal-title":"Proc of IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref40","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc NIPS Autodiff Workshop"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref12","first-page":"4835","article-title":"Joint CTC-attention based end-to-end speech recognition using multitask learning","author":"kim","year":"2017","journal-title":"Proc of IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1109\/JSTSP.2017.2763455","article-title":"Hybrid CTC\/attention architecture for end-to-end speech recognition","volume":"11","author":"shinji","year":"2017","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref14","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ICML Representation Learning Worksop"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"ref17","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 33rd Int Conf Mach Learn"},{"key":"ref18","first-page":"3702","article-title":"An analysis of “attention” in sequence-to-sequence models","author":"rohit","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268924"},{"key":"ref28","author":"navdeep","year":"2015","journal-title":"A neural transducer"},{"key":"ref4","first-page":"604","article-title":"Acoustic modelling with CD-CTC-SMBR LSTM RNNs","author":"sak","year":"2015","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854661"},{"key":"ref6","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"International Conference on Machine Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-334"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref8","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref21","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682539"},{"key":"ref41","first-page":"5824","article-title":"An analysis of incorporating an external language model into a sequence-to-sequence model","author":"anjuli","year":"2018","journal-title":"Proc of IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1910"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682586"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682954"}],"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":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003749.pdf?arnumber=9003749","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:44:17Z","timestamp":1658155457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003749\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003749","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}