{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:17:43Z","timestamp":1771697863930,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2017,7,1]],"date-time":"2017-07-01T00:00:00Z","timestamp":1498867200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000266","name":"EPSRC","doi-asserted-by":"publisher","award":["EP\/I031022\/1"],"award-info":[{"award-number":["EP\/I031022\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Speech Technology; and in part by the European Union under H2020 Project SUMMA","award":["688139"],"award-info":[{"award-number":["688139"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1109\/taslp.2017.2698723","type":"journal-article","created":{"date-parts":[[2017,4,27]],"date-time":"2017-04-27T18:18:04Z","timestamp":1493317084000},"page":"1502-1511","source":"Crossref","is-referenced-by-count":14,"title":["Small-Footprint Highway Deep Neural Networks for Speech Recognition"],"prefix":"10.1109","volume":"25","author":[{"given":"Liang","family":"Lu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steve","family":"Renals","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Distilling\n the knowledge in a neural network","author":"hinton","year":"0","journal-title":"Proc Neural Inf Process Syst Deep Learn Represent Learn Workshop"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2602884"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2560534"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref30","first-page":"1929","article-title":"Dropout: A simple\n way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref37","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc ICLR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","article-title":"Recurrent highway networks","author":"zilly","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472780"},{"key":"ref28","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref29","article-title":"Improving neural networks by preventing co-adaptation of\n feature detectors","author":"hinton","year":"2012"},{"key":"ref2","first-page":"437","article-title":"Conversational\n speech transcription using context-dependent deep neural networks","author":"seide","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","first-page":"3264","article-title":"Transferring\n knowledge from a RNN to a DNN","author":"chan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-911"},{"key":"ref24","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref23","first-page":"153","article-title":"The difficulty of training deep architectures and the effect of\n unsupervised pre-training","author":"erhan","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref26","first-page":"153","article-title":"Greedy layer-wise training of deep networks","volume":"19","author":"bengio","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref10","article-title":"Fitnets: Hints for thin deep nets","author":"adriana","year":"0","journal-title":"Proc ICLR"},{"key":"ref11","first-page":"244","article-title":"Fastfood-approximating kernel expansions in loglinear time","author":"le","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","first-page":"10","article-title":"Scalable minimum Bayes risk training of deep neural network acoustic models using distributed\n Hessian-free optimization","author":"kingsbury","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref12","first-page":"3088","article-title":"Structured transforms for small-footprint deep learning","author":"sindhwani","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref13","article-title":"ACDC: A structured efficient linear\n layer","author":"moczulski","year":"0","journal-title":"Proc ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-39"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846304"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953072"},{"key":"ref17","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref18","first-page":"1209","article-title":"Long short-term memory\n recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3210-1"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1460"},{"key":"ref6","first-page":"2365","article-title":"Restructuring of deep neural\n network acoustic models with singular value decomposition","author":"xue","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/89.260359"},{"key":"ref8","first-page":"1910","article-title":"Learning small-size DNN with output-distribution-based\n criteria","author":"li","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854672"},{"key":"ref9","first-page":"2654","article-title":"Do deep nets really need to be deep","author":"ba","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref46","article-title":"Distant speech recognition experiments using the AMI corpus","author":"renals","year":"2016","journal-title":"New Era for Robust Speech Recognition—Exploting Deep Learning"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430116"},{"key":"ref48","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc Automatic Speech Recognition and Understanding"},{"key":"ref47","article-title":"An introduction to computational networks and the\n computational network toolkit","author":"yu","year":"2014"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638951"},{"key":"ref41","first-page":"2345","article-title":"Sequence-discriminative training of deep\n neural networks","author":"vesel\u00fd","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref43","first-page":"2406","article-title":"Hypothesis spaces for minimum Bayes risk training in large vocabulary speech recognition","author":"gibson","year":"0","journal-title":"Proc INTERSPEECH"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7938821\/07913606.pdf?arnumber=7913606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:15:03Z","timestamp":1642004103000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7913606\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7]]},"references-count":49,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2698723","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,7]]}}}