{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T02:44:00Z","timestamp":1778899440296,"version":"3.51.4"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/icassp.2013.6638963","type":"proceedings-article","created":{"date-parts":[[2013,10,29]],"date-time":"2013-10-29T23:19:46Z","timestamp":1383088786000},"page":"6724-6728","source":"Crossref","is-referenced-by-count":110,"title":["An empirical study of learning rates in deep neural networks for speech recognition"],"prefix":"10.1109","author":[{"given":"Andrew","family":"Senior","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Heigold","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc'Aurelio","family":"Ranzato","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","author":"igel","year":"2000","journal-title":"Improving the Rprop Learning Algorithm"},{"key":"22","article-title":"Improving the speed of neural networks on CPUs","author":"vanhoucke","year":"2011","journal-title":"NIPS Deep Learning Workshop"},{"key":"17","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298623"},{"key":"15","author":"xu","year":"2011","journal-title":"Towards Optimal One Pass Large Scale Learning with Averaged Stochastic Gradient Descent"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225837"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947494"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"11","author":"schaul","year":"2012","journal-title":"No More Pesky Learning Rates"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"21","author":"mnih","year":"2009","journal-title":"Cudamat A CUDA-based matrix class for Python"},{"key":"3","first-page":"211","article-title":"Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters","volume":"2","author":"bridle","year":"1990","journal-title":"NIPS"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660010"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"1","article-title":"Large vocabulary continuous speech recognition with context-dependent DBNHMMs","author":"dahl","year":"2011","journal-title":"ICASSP"},{"key":"10","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":"InterSpeech"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163900"},{"key":"6","article-title":"Krylov subspace descent for deep learning","author":"vinyals","year":"2011","journal-title":"NIPS Deep Learning Workshop"},{"key":"5","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":"InterSpeech"},{"key":"4","doi-asserted-by":"crossref","DOI":"10.1007\/3-540-49430-8_2","article-title":"Efficient backprop","author":"lecun","year":"1998","journal-title":"Neural Networks Tricks of the Trade"},{"key":"9","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":"InterSpeech"},{"key":"8","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"NIPS"}],"event":{"name":"ICASSP 2013 - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2013,5,26]]},"end":{"date-parts":[[2013,5,31]]}},"container-title":["2013 IEEE International Conference on Acoustics, Speech and Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6619549\/6637585\/06638963.pdf?arnumber=6638963","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T22:29:24Z","timestamp":1646951364000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6638963\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp.2013.6638963","relation":{},"subject":[],"published":{"date-parts":[[2013,5]]}}}