{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:23:17Z","timestamp":1776889397507,"version":"3.51.2"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100002465","name":"Delta","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002465","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446807","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11681-11685","source":"Crossref","is-referenced-by-count":7,"title":["Semi-Autoregressive Streaming ASR with Label Context"],"prefix":"10.1109","author":[{"given":"Siddhant","family":"Arora","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Saon","sequence":"additional","affiliation":[{"name":"IBM Research,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[{"name":"IBM Research,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3328283"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref5","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"CoRR"},{"key":"ref6","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. NeurIPS","author":"Chorowski"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414716"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3018"},{"key":"ref13","article-title":"Listen and fill in the missing letters: Non-autoregressive transformer for speech recognition","author":"Chen","year":"2019","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2086"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-9996"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-911"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462497"},{"key":"ref25","first-page":"5067","article-title":"An online sequence-to-sequence model using partial conditioning","volume-title":"Proc. NeurIPS","author":"Jaitly"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682954"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003749"},{"key":"ref28","article-title":"Streaming transformer ASR with blockwise synchronous inference","author":"Tsunoo","year":"2020","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383517"},{"key":"ref30","article-title":"Transformer transducer: One model unifying streaming and non-streaming speech recognition","author":"Tripathi","year":"2020","journal-title":"CoRR"},{"key":"ref31","article-title":"RNN-T for latency controlled ASR with improved beam search","author":"Jain","year":"2019","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268937"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746390"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1556"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1044"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00350"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_27"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2841"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3233237"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1333"},{"key":"ref42","first-page":"3935","article-title":"Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks","author":"Rousseau","year":"2014","journal-title":"LREC"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.396"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6441"},{"key":"ref48","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"CoRR"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10114"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446807.pdf?arnumber=10446807","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:39:32Z","timestamp":1722573572000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446807\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446807","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}