{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:23Z","timestamp":1760245043769,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/asru.2017.8268933","type":"proceedings-article","created":{"date-parts":[[2018,1,25]],"date-time":"2018-01-25T21:43:53Z","timestamp":1516916633000},"page":"178-184","source":"Crossref","is-referenced-by-count":4,"title":["Sequence training of DNN acoustic models with natural gradient"],"prefix":"10.1109","author":[{"given":"Adnan","family":"Haider","sequence":"first","affiliation":[]},{"given":"Philip C.","family":"Woodland","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0182"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518545"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-603","article-title":"Hypothesis Spaces for Minimum Bayes' Risk Training in Large Vocabulary Speech Recognition","author":"gibson","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref14","article-title":"Binary Codes Capable of Correcting Deletions, Insertions, and Reversals","volume":"10","author":"levenshtein","year":"1966","journal-title":"Soviet Physics Doklady"},{"key":"ref15","article-title":"Minimum Phone Error and I-smoothing for Improved Discriminative Training","author":"povey","year":"2002","journal-title":"Proc International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref16","article-title":"Revisiting Natural Gradient for Deep Networks","author":"pascanu","year":"2014","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref17","article-title":"Natural Neural Networks","author":"desjardins","year":"2015","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS)"},{"journal-title":"New Insights and Perspectives on the Natural Gradient Method","year":"2014","author":"martens","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017746"},{"key":"ref4","article-title":"Deep Learning via Hessian-free Optimization","author":"martens","year":"2010","journal-title":"Proc International Conference on Machine Learning (ICML)"},{"journal-title":"Optimization Methods for Large-Scale Machine Learning","year":"2016","author":"bottou","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2284378"},{"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","article-title":"Parallel Training of DNNs with Natural Gradient and Parameter Averaging","author":"povey","year":"2015","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707750"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/2000000004"},{"key":"ref1","article-title":"Greedy Layer-Wise Training of Deep Networks","author":"bengio","year":"2007","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref20","article-title":"Neural learning in Structured Parameter Spaces-Natural Riemannian Gradient","author":"amari","year":"1997","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.1.147"},{"key":"ref21","article-title":"An Introduction to the Conjugate Gradient Method Without the Agonizing Pain","author":"shewchuk","year":"1994","journal-title":"Technical Report Carnegie Mellon University"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404856"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404863"},{"journal-title":"The HTK Book (for HTK 3 5)","year":"2015","author":"young","key":"ref26"},{"key":"ref25","article-title":"A General Artificial Neural Network Extension for HTK","author":"zhang","year":"2015","journal-title":"Proc INTERSPEECH"}],"event":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2017,12,16]]},"location":"Okinawa, Japan","end":{"date-parts":[[2017,12,20]]}},"container-title":["2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8260578\/8268903\/08268933.pdf?arnumber=8268933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T06:18:31Z","timestamp":1660371511000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8268933\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/asru.2017.8268933","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}