{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:27:22Z","timestamp":1775230042826,"version":"3.50.1"},"reference-count":38,"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\/icassp39728.2021.9413905","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"5639-5643","source":"Crossref","is-referenced-by-count":23,"title":["Efficient Knowledge Distillation for RNN-Transducer Models"],"prefix":"10.1109","author":[{"given":"Sankaran","family":"Panchapagesan","sequence":"first","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel S.","family":"Park","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chung-Cheng","family":"Chiu","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Shangguan","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiao","family":"Liang","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Gruenstein","sequence":"additional","affiliation":[{"name":"Google LLC,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","article-title":"Dynamic Sparsity Neural Networks for Automatic Speech Recognition","author":"wu","year":"2021","journal-title":"ICASSP"},{"key":"ref33","article-title":"Gradient Based Pruning","author":"yang","year":"2019"},{"key":"ref32","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"zhu","year":"2018","journal-title":"ICLRE"},{"key":"ref31","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":"InterSpeech"},{"key":"ref30","article-title":"Specaugment on large scale datasets","author":"park","year":"2020","journal-title":"ICASSP"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"ref36","article-title":"Universal ASR: Unify and Improve Streaming ASR with Full-Context Modeling","author":"yu","year":"2020"},{"key":"ref35","article-title":"Block-sparse recurrent neural networks","author":"narang","year":"2017"},{"key":"ref34","article-title":"SNIP: Single-shot Network Pruning based on Connection Sensitivity","author":"lee","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2442"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639610"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref14","article-title":"The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions","author":"pearce","year":"2000","journal-title":"InterSpeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953163"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953072"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-614"},{"key":"ref19","article-title":"Acoustic modelling with cd-ctc-smbr lstm rnns","author":"sak","year":"2015","journal-title":"ASRU"},{"key":"ref28","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref4","article-title":"Improving Noise Robustness of Automatic Speech Recognition via Parallel Data and Teacher-student Learning","author":"mo\u0161ner","year":"2019","journal-title":"ICASSP"},{"key":"ref27","article-title":"Group normalization","author":"wu","year":"2018","journal-title":"ECCV"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref5","article-title":"Sequence Transduction with Recurrent Neural Networks","author":"graves","year":"2012"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"ref2","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref1","article-title":"Model compression","author":"bucilu?","year":"2006","journal-title":"SIGKDD"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461995"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639629"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682671"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003776"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1952"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref25","article-title":"Optimizing Speech Recognition for the Edge","author":"shangguan","year":"2020"}],"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\/09413905.pdf?arnumber=9413905","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:42Z","timestamp":1659486042000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413905\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413905","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}