{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:47:44Z","timestamp":1753602464011},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414607","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"source":"Crossref","is-referenced-by-count":45,"title":["Cascaded Encoders for Unifying Streaming and Non-Streaming ASR"],"prefix":"10.1109","author":[{"given":"Arun","family":"Narayanan","sequence":"first","affiliation":[]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[]},{"given":"Ruoming","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Jiahui","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Chung-Cheng","family":"Chiu","sequence":"additional","affiliation":[]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[]},{"given":"Ehsan","family":"Variani","sequence":"additional","affiliation":[]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-264"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home","author":"kim","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref37","article-title":"Adam: A method for Stochastic Optimization","author":"kingma","year":"2014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref35","article-title":"Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling","author":"shen","year":"2019"},{"key":"ref34","first-page":"265","article-title":"Tensorflow: A System for Large-scale Machine Learning","author":"abadi","year":"2016","journal-title":"Proc of of OSDI"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref11","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"yeh","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053606"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.889790"},{"key":"ref15","first-page":"1784","article-title":"Deliberation networks: Sequence generation beyond one-pass decoding","author":"xia","year":"2017","journal-title":"Proc of NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016292"},{"key":"ref18","article-title":"Sequence to multi-sequence learning via conditional chain mapping for mixture signals","author":"shi","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref28","article-title":"FastEmit: Low-latency streaming asr with sequence-level emission regularization","author":"yu","year":"2021","journal-title":"Proc of ICASSP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"ref27","first-page":"6069","article-title":"Towards fast and accurate streaming end-to-end asr","author":"li","year":"2020","journal-title":"Proc of ICASSP"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref6","first-page":"577","article-title":"Attention-Based Models for Speech Recognition","author":"chorowski","year":"2015","journal-title":"Proc of NeurIPS"},{"key":"ref29","article-title":"Minimum word error rate training for attention-based sequence-to-sequence models","author":"prabhavalkar","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref8","article-title":"Sequence Transduction with Recurrent Neural Networks","author":"graves","year":"2012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"ref22","article-title":"Transformer transducer: One model unifying streaming and non-streaming speech recognition","author":"tripathi","year":"2020"},{"key":"ref21","article-title":"Universal ASR: Unify and improve streaming asr with full-context modeling","author":"yu","year":"2020"},{"key":"ref24","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc of NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2539499"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414607.pdf?arnumber=9414607","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:12Z","timestamp":1652197272000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414607\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414607","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}