{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T12:34:15Z","timestamp":1791549255136,"version":"4.3.4"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800614","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"11-15","source":"Crossref","is-referenced-by-count":2,"title":["CUSIDE-T: Chunking, Simulating Future and Decoding for Transducer Based Streaming ASR"],"prefix":"10.1109","author":[{"given":"Wenbo","family":"Zhao","sequence":"first","affiliation":[{"name":"China Unicom (Guangdong) Industrial Internet Co., Ltd."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuan","family":"Yu","sequence":"additional","affiliation":[{"name":"China Unicom (Guangdong) Industrial Internet Co., Ltd."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijian","family":"Ou","sequence":"additional","affiliation":[{"name":"Tsinghua University,Speech Processing and Machine Intelligence (SPMI) Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","article-title":"Sequence transduction with recurrent neural networks","author":"Graves","year":"2012","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"End-to-end continuous speech recognition using attention-based recurrent nn: First results","volume-title":"NIPS 2014 Workshop on Deep Learning, December 2014","author":"Chorowski","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472621"},{"key":"ref5","article-title":"Attention-based models for speech recognition","volume":"28","author":"Chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref6","article-title":"Monotonic chunkwise attention","author":"Chiu","year":"2017","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1953"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11214"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682256"},{"key":"ref10","article-title":"U2++: Unified two-pass bidirectional end-to-end model for speech recognition","author":"Wu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Unified streaming and non-streaming two-pass end-to-end model for speech recognition","author":"Zhang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746682"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414607"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"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":"ref20","article-title":"Dual-mode ASR: Unify and improve streaming ASR with full-context modeling","volume-title":"International Conference on Learning Representations","author":"Yu","year":"2021"},{"key":"ref21","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"Hannun","year":"2014","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10576"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2732"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003822"},{"key":"ref28","first-page":"187","article-title":"KenLM: Faster and smaller language model queries","volume-title":"Proceedings of the sixth workshop on statistical machine translation","author":"Heafield","year":"2011"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Beijing, China","start":{"date-parts":[[2024,11,7]]},"end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800614.pdf?arnumber=10800614","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T19:28:43Z","timestamp":1736969323000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800614\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800614","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}