{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:55:21Z","timestamp":1774367721278,"version":"3.50.1"},"reference-count":31,"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\/icassp39728.2021.9413692","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6558-6562","source":"Crossref","is-referenced-by-count":11,"title":["Improving Streaming Automatic Speech Recognition with Non-Streaming Model Distillation on Unsupervised Data"],"prefix":"10.1109","author":[{"given":"Thibault","family":"Doutre","sequence":"first","affiliation":[]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[]},{"given":"Min","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Zhiyun","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Chung-Cheng","family":"Chiu","sequence":"additional","affiliation":[]},{"given":"Ruoming","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Arun","family":"Narayanan","sequence":"additional","affiliation":[]},{"given":"Ananya","family":"Misra","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Liangliang","family":"Cao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref31","article-title":"Common Voice: A Massively-Multilingual Speech Corpus","author":"ardila","year":"2020"},{"key":"ref30","first-page":"7669","article-title":"Libri-light: A benchmark for ASR with limited or no supervision","author":"kahn","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2442"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-1470","article-title":"Improved Noisy Student Training for Automatic Speech Recognition","author":"park","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref16","article-title":"Revisiting self-training for neural sequence generation","author":"he","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.211"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref28","article-title":"Streaming Transformer ASR with Blockwise Synchronous Inference","author":"tsunoo","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1292"},{"key":"ref3","article-title":"Transformer-Transducer: End-to-End Speech Recognition with Self-Attention","author":"yeh","year":"2019"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref29","article-title":"Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling","author":"yu","year":"2021","journal-title":"ICLRE"},{"key":"ref5","first-page":"6069","article-title":"Towards fast and accurate streaming end-to-end ASR","author":"li","year":"2020","journal-title":"Proc ICASSP"},{"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","article-title":"Towards online end-to-end transformer automatic speech recognition","author":"tsunoo","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref1","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref20","article-title":"RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions","author":"chiu","year":"2020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref24","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","author":"lee","year":"2013","journal-title":"Workshop on Challenges in Representation Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref25","first-page":"5206","article-title":"Librispeech: an ASR corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"Proc ICASSP"}],"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\/09413692.pdf?arnumber=9413692","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:27:01Z","timestamp":1672129621000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413692\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413692","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}