{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T22:55:58Z","timestamp":1771023358026,"version":"3.50.1"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"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":[[2020,11,1]]},"DOI":"10.1109\/ieeeconf51394.2020.9443456","type":"proceedings-article","created":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T01:32:35Z","timestamp":1622770355000},"page":"277-283","source":"Crossref","is-referenced-by-count":20,"title":["A Review of On-Device Fully Neural End-to-End Automatic Speech Recognition Algorithms"],"prefix":"10.1109","author":[{"given":"Chanwoo","family":"Kim","sequence":"first","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]},{"given":"Dhananjaya","family":"Gowda","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]},{"given":"Dongsoo","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]},{"given":"Jiyeon","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]},{"given":"Ankur","family":"Kumar","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]},{"given":"Sungsoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]},{"given":"Abhinav","family":"Garg","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]},{"given":"Changwoo","family":"Han","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3230"},{"key":"ref32","article-title":"Deeptwist: Learning model compression via occasional weight distortion","author":"lee","year":"2018","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003976"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003973"},{"key":"ref37","article-title":"Cold fusion: Training seq2seq models together with language models","author":"sriram","year":"2017"},{"key":"ref36","article-title":"On using monolingual corpora in neural machine translation","author":"g\u00fcl\u00e7ehre","year":"2015","journal-title":"CoRR"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"523","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"379","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 Interspeech 2017"},{"key":"ref12","first-page":"577","article-title":"Attention-based models for speech recognition","volume":"28","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref14","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383583"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref17","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004027"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref28","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2545928"},{"key":"ref27","article-title":"Keras","author":"chollet","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3227"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"2734","DOI":"10.21437\/Interspeech.2014-157","article-title":"Robust speech recognition using temporal masking and thresholding algorithma","author":"kim","year":"2014","journal-title":"2014 IEEE INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373230"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2566"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1025"},{"key":"ref20","first-page":"10620","article-title":"Fully neural network based speech recognition on mobile and embedded devices","volume":"31","author":"park","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref45","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","author":"han","year":"2016","journal-title":"4th International Conference on Learning Representations ICLR 2016"},{"key":"ref22","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"0","journal-title":"International Conference of Machine Learning (ICML) 2012 Workshop on Representation Learning"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3174"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2460"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"939","DOI":"10.21437\/Interspeech.2017-233","article-title":"A comparison of sequence-to-sequence models for speech recognition","author":"prabhavalkar","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3172"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"6645","DOI":"10.1109\/ICASSP.2013.6638947","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"2013","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472820"},{"key":"ref26","article-title":"Monotonic chunkwise attention","author":"chiu","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS.2014.6986082"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"}],"event":{"name":"2020 54th Asilomar Conference on Signals, Systems, and Computers","location":"Pacific Grove, CA, USA","start":{"date-parts":[[2020,11,1]]},"end":{"date-parts":[[2020,11,4]]}},"container-title":["2020 54th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9443248\/9443268\/09443456.pdf?arnumber=9443456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T23:58:09Z","timestamp":1659484689000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9443456\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,1]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf51394.2020.9443456","relation":{},"subject":[],"published":{"date-parts":[[2020,11,1]]}}}