{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:40:26Z","timestamp":1775281226740,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2013,11,1]],"date-time":"2013-11-01T00:00:00Z","timestamp":1383264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2013,11]]},"DOI":"10.1109\/tasl.2013.2284378","type":"journal-article","created":{"date-parts":[[2013,10,3]],"date-time":"2013-10-03T18:02:10Z","timestamp":1380823330000},"page":"2267-2276","source":"Crossref","is-referenced-by-count":42,"title":["Optimization Techniques to Improve Training Speed of Deep Neural Networks for Large Speech Tasks"],"prefix":"10.1109","volume":"21","author":[{"given":"Tara N.","family":"Sainath","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian","family":"Kingsbury","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hagen","family":"Soltau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.879814"},{"key":"ref33","author":"strang","year":"2009","journal-title":"Introduction to Linear Algebra"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/08997660260028683"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.1.147"},{"key":"ref30","article-title":"Krylov subspace descent for deep learning","author":"vinyals","year":"2011","journal-title":"Proc NIPS Workshop Optimiz Hierarch Learn"},{"key":"ref37","author":"sainath","year":"2012","journal-title":"?Improvements in using deep belief networks for large vocabulary continuous speech recognition ?"},{"key":"ref36","article-title":"Low-rank matrix factorization for deep belief network training","author":"sainath","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/89.759034"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2010.5700829"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-22","article-title":"Parallel training of neural networks for speech recognition","author":"vesely","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390224"},{"key":"ref12","article-title":"Deep learning via hessian-free optimization","author":"martens","year":"2010","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref14","article-title":"Parallelized stochastic gradient descent","author":"zinkevich","year":"2010","journal-title":"Proc NIPS"},{"key":"ref15","author":"hinton","year":"2010","journal-title":"?A practical guide to training restricted Boltzmann machines ?"},{"key":"ref16","article-title":"Improving training time of deep belief networks through hybrid pre-training and larger batch sizes","author":"sainath","year":"2012","journal-title":"Proc NIPS Workshop Log-linear Models"},{"key":"ref17","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc NIPS"},{"key":"ref18","article-title":"Map-reduce for machine learning on multicore","author":"chu","year":"2007","journal-title":"Proc NIPS"},{"key":"ref19","article-title":"Optimal brain damage","author":"lecun","year":"1990","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288863"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-10","article-title":"Application of pretrained deep neural networks to large vocabulary speech recognition","author":"jaitly","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref3","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-169","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/10079923X"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-3","article-title":"Scalable minimum Bayes risk training of deep neural network acoustic models using distributed Hessian-free optimization","author":"kingsbury","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"ref7","article-title":"Roles of pre-training and fine-tuning in context-dependent DBN-HMMs for real-world speech recognition","author":"yu","year":"2010","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref9","article-title":"On optimization methods for deep learning","author":"le","year":"2011","journal-title":"Proc ICML"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288897"},{"key":"ref22","first-page":"706","article-title":"Convolutional neural networks for large vocabulary speech recognition","author":"sainath","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref21","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s12532-013-0053-8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2007.00591.x"},{"key":"ref26","first-page":"1","article-title":"Exploring strategies for training deep neural networks","volume":"1","author":"larochelle","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553486"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376\/6631496\/06619439.pdf?arnumber=6619439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T21:15:00Z","timestamp":1646687700000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6619439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,11]]},"references-count":38,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2013.2284378","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"value":"1558-7916","type":"print"},{"value":"1558-7924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,11]]}}}