{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:37:06Z","timestamp":1776109026734,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"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\/icassp39728.2021.9413803","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6004-6008","source":"Crossref","is-referenced-by-count":46,"title":["FastEmit: Low-Latency Streaming ASR with Sequence-Level Emission Regularization"],"prefix":"10.1109","author":[{"given":"Jiahui","family":"Yu","sequence":"first","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Chung-Cheng","family":"Chiu","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Shuo-yiin","family":"Chang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Yanzhang","family":"He","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Arun","family":"Narayanan","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Anmol","family":"Gulati","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Ruoming","family":"Pang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1898"},{"key":"ref12","article-title":"Universal asr: Unify and improve streaming asr with full-context modeling","author":"yu","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1292"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461929"},{"key":"ref15","article-title":"Listen, Attend and Spell","author":"chan","year":"2015","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-2875","article-title":"Parallel rescoring with transformer for streaming on-device speech recognition","author":"li","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461809"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-284"},{"key":"ref4","article-title":"Sequence Transduction with Recurrent Neural Networks","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1059"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref7","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"yeh","year":"2019"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2015-350","article-title":"Fast and accurate recurrent neural network acoustic models for speech recognition","author":"sak","year":"2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054715"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref24","article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","author":"shen","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003854"}],"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\/09413803.pdf?arnumber=9413803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:27:45Z","timestamp":1672129665000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413803\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413803","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}