{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:52:07Z","timestamp":1780501927817,"version":"3.54.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682336","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"6381-6385","source":"Crossref","is-referenced-by-count":328,"title":["Streaming End-to-end Speech Recognition for Mobile Devices"],"prefix":"10.1109","author":[{"given":"Yanzhang","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ian","family":"McGraw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raziel","family":"Alvarez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ding","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Rybach","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anjuli","family":"Kannan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruoming","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiao","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deepti","family":"Bhatia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Shangguan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Golan","family":"Pundak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khe Chai","family":"Sim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom","family":"Bagby","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo-yiin","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kanishka","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Gruenstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682172"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"key":"ref33","article-title":"Reducing the Computational Complexity for Whole Word Models","author":"soltau","year":"2017","journal-title":"ASRU"},{"key":"ref32","article-title":"Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref30","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2017","journal-title":"Google Tech Rep"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref36","article-title":"Composition-based on-the-fly rescoring for salient n-gram biasing","author":"hall","year":"2015","journal-title":"InterSpeech"},{"key":"ref35","article-title":"Introducing the Model Optimization Toolkit for TensorFlow","author":"alvarez","year":"0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref10","article-title":"Listen, attend and spell","author":"chan","year":"2015","journal-title":"CoRR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref12","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"CoRR"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc ICML"},{"key":"ref17","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"3707","DOI":"10.21437\/Interspeech.2017-1566","article-title":"Neural speech recognizer: Acoustic-to-word lstm model for large vocabulary speech recognition","author":"soltau","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2416"},{"key":"ref4","article-title":"Convolutional neural networks for small-footprint keyword spotting","author":"sainath","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-128"},{"key":"ref3","first-page":"61","article-title":"Your Word is my Command","author":"schalkwyk","year":"2010","journal-title":"Google Search by Voice A Case Study"},{"key":"ref6","first-page":"474","article-title":"Streaming small-footprint keyword spotting using sequence-to-sequence models","author":"he","year":"2017","journal-title":"Proc ASRU"},{"key":"ref29","article-title":"Deep Context: End-to-End Contextual Speech Recognition","author":"pundak","year":"2018","journal-title":"Proc SLT"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1737","article-title":"Convolutional recurrent neural networks for small-footprint keyword spotting","author":"arik","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.2003-147","article-title":"Speechalator: Two-way speech-to-speech translation on a consumer PDA","author":"waibel","year":"2003","journal-title":"Proc EUROSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683557"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518869"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472820"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref46","article-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","author":"abadi","year":"2015"},{"key":"ref20","article-title":"Speech recognition with deep neural networks","author":"graves","year":"2012","journal-title":"Proc ICASSP"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref22","article-title":"Monotonic chunkwise alignments","author":"chiu","year":"2017","journal-title":"Proc ICLR"},{"key":"ref21","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":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-35"},{"key":"ref24","article-title":"Layer Normalization","author":"ba","year":"2016","journal-title":"CoRR"},{"key":"ref41","article-title":"Sequence-based class tagging for robust transcription in asr","author":"vasserman","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref23","article-title":"Bringing Contextual Information to Google Speech Recognition","author":"aleksic","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generated 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 INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-264"},{"key":"ref25","article-title":"Improving the Efficiency of Forward-Backward Algorithm using Batched Computation in TensorFlow","author":"sim","year":"2017","journal-title":"ASRU"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682336.pdf?arnumber=8682336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T05:36:18Z","timestamp":1663306578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682336","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}