{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:11Z","timestamp":1775230151053,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054188","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6059-6063","source":"Crossref","is-referenced-by-count":99,"title":["A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality and Latency"],"prefix":"10.1109","author":[{"given":"Tara N.","family":"Sainath","sequence":"first","affiliation":[]},{"given":"Yanzhang","family":"He","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[]},{"given":"Arun","family":"Narayanan","sequence":"additional","affiliation":[]},{"given":"Ruoming","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Antoine","family":"Bruguier","sequence":"additional","affiliation":[]},{"given":"Shuo-yiin","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Raziel","family":"Alvarez","sequence":"additional","affiliation":[]},{"given":"Zhifeng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Chung-Cheng","family":"Chiu","sequence":"additional","affiliation":[]},{"given":"David","family":"Garcia","sequence":"additional","affiliation":[]},{"given":"Alex","family":"Gruenstein","sequence":"additional","affiliation":[]},{"given":"Ke","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Anjuli","family":"Kannan","sequence":"additional","affiliation":[]},{"given":"Qiao","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Ian","family":"McGraw","sequence":"additional","affiliation":[]},{"given":"Cal","family":"Peyser","sequence":"additional","affiliation":[]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[]},{"given":"Golan","family":"Pundak","sequence":"additional","affiliation":[]},{"given":"David","family":"Rybach","sequence":"additional","affiliation":[]},{"given":"Yuan","family":"Shangguan","sequence":"additional","affiliation":[]},{"given":"Yash","family":"Sheth","sequence":"additional","affiliation":[]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[]},{"given":"Mirko","family":"Visontai","sequence":"additional","affiliation":[]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Ding","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1203","article-title":"Effectively Building Tera Scale MaxEnt Language Models Incorporating Non-Linguistic Signals","author":"biadsy","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461809"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-496"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-284"},{"key":"ref16","article-title":"A unified end-pointer using multitask and multidomain training","author":"chang","year":"2019","journal-title":"Proc ASRU"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683109"},{"key":"ref18","first-page":"799","article-title":"Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition","author":"schuster","year":"2005","journal-title":"Artificial Neural Networks Formal Models and Their Applications-ICANN"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref4","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref28","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":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1475"},{"key":"ref6","first-page":"193","article-title":"Exploring architectures, data and units for streaming end-to-end speech recognition with rnn-transducer","author":"rao","year":"2017","journal-title":"Proc ASRU"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref29","article-title":"Improving Wideband Speech Rcognition using Mixed-bandwidth Training Data in CD-DNN-HMM","author":"li","year":"2012","journal-title":"Proc SLT"},{"key":"ref8","first-page":"4835","article-title":"Joint CTC-attention based end-to-end speech recognition using multi-task learning","author":"kim","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref7","article-title":"Listen, attend and spell","author":"chan","year":"2015","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003913"},{"key":"ref9","article-title":"Monotonic chunkwise attention","author":"chiu","year":"2018","journal-title":"Proc ICLR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1566"},{"key":"ref22","article-title":"Varcon open source dictionary","author":"atkinson","year":"0"},{"key":"ref21","author":"jurafsky","year":"2000","journal-title":"Speech and Language Processing"},{"key":"ref24","article-title":"Attention Is All You Need","author":"vaswani","year":"2017","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref26","article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","author":"shen","year":"2019"},{"key":"ref25","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2015"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054188.pdf?arnumber=9054188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:08:58Z","timestamp":1656374938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054188\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054188","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}