{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T20:22:00Z","timestamp":1781382120158,"version":"3.54.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1617640"],"award-info":[{"award-number":["CNS-1617640"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput."],"published-print":{"date-parts":[[2020,3,1]]},"DOI":"10.1109\/tc.2019.2954495","type":"journal-article","created":{"date-parts":[[2019,11,20]],"date-time":"2019-11-20T21:08:18Z","timestamp":1574284098000},"page":"441-452","source":"Crossref","is-referenced-by-count":71,"title":["Grow and Prune Compact, Fast, and Accurate LSTMs"],"prefix":"10.1109","volume":"69","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3098-2714","authenticated-orcid":false,"given":"Xiaoliang","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6481-6389","authenticated-orcid":false,"given":"Hongxu","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1539-0369","authenticated-orcid":false,"given":"Niraj K.","family":"Jha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4012"},{"key":"ref33","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2017","journal-title":"arXiv 1712 01887"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref36","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","author":"alistarh","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3122-7"},{"key":"ref34","article-title":"Speech recognition using DeepSpeech2","author":"naren","year":"2018"},{"key":"ref28","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref29","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref1","article-title":"Gradient flow in recurrent nets: The difficulty of learning long-term dependencies","author":"hochreiter","year":"2001","journal-title":"A Field Guide to Dynamical Recurrent Neural Networks"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMSCS.2018.2821154"},{"key":"ref22","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","author":"han","year":"2015","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178826"},{"key":"ref24","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"xu","year":"2015","journal-title":"arXiv 1505 00853"},{"key":"ref23","article-title":"DSD: Regularizing deep neural networks with dense-sparse-dense training flow","author":"han","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","article-title":"Image captioning in Torch","author":"karpathy","year":"2016"},{"key":"ref25","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc NIPS Autodiff Workshop"},{"key":"ref50","first-page":"2285","article-title":"Compressing neural networks with the hashing trick","author":"chen","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-522"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01166"},{"key":"ref56","article-title":"Exploring sparsity in recurrent neural networks","author":"narang","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288897"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_12"},{"key":"ref53","article-title":"Compressing deep convolutional networks using vector quantization","author":"gong","year":"2014","journal-title":"arXiv 1412 6115"},{"key":"ref52","article-title":"Improving the speed of neural networks on CPUs","volume":"1","author":"vanhoucke","year":"2011","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMSCS.2018.2864297"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CICC.2018.8357069"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref12","article-title":"Recurrent neural network regularization","author":"zaremba","year":"2014","journal-title":"arXiv 1409 2329"},{"key":"ref13","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Proc Neural Inf Process Syst"},{"key":"ref14","article-title":"Zoneout: Regularizing RNNs by randomly preserving hidden activations","author":"krueger","year":"2016","journal-title":"arXiv 1606 01305"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2019.2914438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3020078.3021745"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref19","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref3","first-page":"173","article-title":"Deep Speech 2 : End-to-end speech recognition in English and Mandarin","volume":"48","author":"amodei","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref6","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv 1609 08144"},{"key":"ref5","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","article-title":"iOS 10: Siri now works in third-party apps, comes with extra AI features","author":"smith","year":"2017","journal-title":"BGR Retrieved"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472821"},{"key":"ref9","article-title":"Deep Speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014","journal-title":"arXiv 1412 5567"},{"key":"ref46","first-page":"2148","article-title":"Predicting parameters in deep learning","author":"denil","year":"2013","journal-title":"Proc 26th Int Conf Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref47","first-page":"1269","article-title":"Exploiting linear structure within convolutional networks for efficient evaluation","author":"denton","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-477"},{"key":"ref43","article-title":"How to construct deep recurrent neural networks","author":"pascanu","year":"2013","journal-title":"arXiv 1312 6026"}],"container-title":["IEEE Transactions on Computers"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/12\/8989854\/8907435-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/12\/8989854\/08907435.pdf?arnumber=8907435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:09:58Z","timestamp":1651068598000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8907435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,1]]},"references-count":58,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tc.2019.2954495","relation":{},"ISSN":["0018-9340","1557-9956","2326-3814"],"issn-type":[{"value":"0018-9340","type":"print"},{"value":"1557-9956","type":"electronic"},{"value":"2326-3814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3,1]]}}}