{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T14:46:38Z","timestamp":1769006798761,"version":"3.49.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383504","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"8-14","source":"Crossref","is-referenced-by-count":5,"title":["Streaming Attention-Based Models with Augmented Memory for End-To-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Ching-Feng","family":"Yeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangyang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"Chan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael L.","family":"Seltzer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003920"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462497"},{"key":"ref16","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"yeh","year":"2019"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-2059","article-title":"Contextnet: Improving convolutional neural networks for automatic speech recognition with global context","author":"han","year":"2020"},{"key":"ref18","article-title":"Transformers with convolutional context for asr","author":"mohamed","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-2079","article-title":"Streaming transformer-based acoustic models using self-attention with augmented memory","author":"wu","year":"2020"},{"key":"ref3","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1363"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1995"},{"key":"ref7","article-title":"Transformer-based acoustic modeling for hybrid speech recognition","author":"wang","year":"2020","journal-title":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Quartznet: Deep automatic speech recognition with 1d time-channel separable convolutions","author":"kriman","year":"2020","journal-title":"International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref25","article-title":"On using monolingual corpora in neural machine translation","author":"gulcehre","year":"2015"}],"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\/09383504.pdf?arnumber=9383504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T21:30:52Z","timestamp":1622496652000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383504\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383504","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}