{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:22Z","timestamp":1760245042049,"version":"3.28.0"},"reference-count":7,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1109\/asru.2013.6707750","type":"proceedings-article","created":{"date-parts":[[2014,1,10]],"date-time":"2014-01-10T15:07:23Z","timestamp":1389366443000},"page":"321-325","source":"Crossref","is-referenced-by-count":5,"title":["Combining stochastic average gradient and Hessian-free optimization for sequence training of deep neural networks"],"prefix":"10.1109","author":[{"given":"Pierre","family":"Dognin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vaibhava","family":"Goel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"3","first-page":"6664","article-title":"Error back propagation for sequence training of contextdependent deep networks for conversational speech transcription","author":"su","year":"2013","journal-title":"ICASSP"},{"key":"2","first-page":"105","article-title":"Minimum phone error and i-smoothing for improved discriminative training","author":"povey","year":"2002","journal-title":"ICASSP"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"7","article-title":"Large scale online learning","volume":"16","author":"bottou","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"6","article-title":"Training neural networks with stochastic hessian-free optimization","author":"kiros","year":"2013","journal-title":"International Conference on Learning Representations"},{"key":"5","first-page":"735","article-title":"Deep learning via hessian-free optimization","author":"martens","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)"},{"key":"4","first-page":"2672","article-title":"A stochastic gradient method with an exponential convergence rate for finite training sets","volume":"25","author":"roux","year":"2012","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2013 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","start":{"date-parts":[[2013,12,8]]},"location":"Olomouc, Czech Republic","end":{"date-parts":[[2013,12,12]]}},"container-title":["2013 IEEE Workshop on Automatic Speech Recognition and Understanding"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6695806\/6707689\/06707750.pdf?arnumber=6707750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,22]],"date-time":"2017-03-22T21:44:21Z","timestamp":1490219061000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6707750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12]]},"references-count":7,"URL":"https:\/\/doi.org\/10.1109\/asru.2013.6707750","relation":{},"subject":[],"published":{"date-parts":[[2013,12]]}}}