{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:36:29Z","timestamp":1753601789542,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688121","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T15:31:00Z","timestamp":1643902260000},"page":"403-410","source":"Crossref","is-referenced-by-count":4,"title":["Two-Pass End-to-End ASR Model Compression"],"prefix":"10.1109","author":[{"given":"Nauman","family":"Dawalatabad","sequence":"first","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tushar","family":"Vatsal","sequence":"additional","affiliation":[{"name":"Amazon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashutosh","family":"Gupta","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungsoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shatrughan","family":"Singh","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dhananjaya","family":"Gowda","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chanwoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref32","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSNT.2013.6967289"},{"key":"ref35","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref10","article-title":"Listen, attend and spell","author":"chan","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"ref13","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref14","first-page":"3697","article-title":"Efficient knowledge distillation from an ensemble of teachers","author":"fukuda","year":"0","journal-title":"Proc of Interspeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICEngTechnol.2017.8308186"},{"key":"ref16","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Long short-term memory recurrent neural network ar-chitectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","article-title":"Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network","volume":"404","author":"sherstinsky","year":"2020","journal-title":"Physica D Nonlinear Phenomena"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004027"},{"key":"ref27","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414502"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003976"},{"key":"ref29","article-title":"Neural machine translation of rare words with subword units","author":"sennrich","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003936"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF51394.2020.9443456"},{"key":"ref7","first-page":"3371","article-title":"Streaming on-device end-to-end ASR system for privacy-sensitive voicetyping","author":"garg","year":"0","journal-title":"Proc of Interspeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1341"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-911"},{"key":"ref22","article-title":"Improved training for online end-to-end speech recognition systems","author":"kim","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.150"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2442"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461995"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref25","article-title":"Efficient knowledge distillation for rnn-transducer models","author":"panchapagesan","year":"2020","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688121.pdf?arnumber=9688121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T16:42:07Z","timestamp":1652719327000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688121","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}