{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:11:53Z","timestamp":1729635113374,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/asru.2015.7404771","type":"proceedings-article","created":{"date-parts":[[2016,2,12]],"date-time":"2016-02-12T08:55:42Z","timestamp":1455267342000},"page":"37-44","source":"Crossref","is-referenced-by-count":2,"title":["Hybrid DNN-Latent structured SVM acoustic models for continuous speech recognition"],"prefix":"10.1109","author":[{"given":"Suman","family":"Ravuri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1038"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-007-9040-x"},{"key":"ref31","first-page":"2345","article-title":"Sequence-discriminative training of deep neural networks","author":"vesely","year":"2013","journal-title":"14th Annual Conference of the International Speech Communication Association Interspeech 2013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"4057","DOI":"10.1109\/ICASSP.2008.4518545","article-title":"Boosted MMI for model and feature-space discriminative training","author":"povey","year":"2008","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing ICASSP 2008"},{"key":"ref11","first-page":"265","article-title":"Large margin gaussian mixture modeling for phonetic classification and recognition","author":"sha","year":"2006","journal-title":"2006 IEEE International Conference on Acoustics Speech and Signal Processing ICASSP 2006"},{"key":"ref12","first-page":"25","article-title":"Max-margin markov networks","volume":"16","author":"taskar","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"1453","article-title":"Large margin methods for structured and interdependent output variables","volume":"6","author":"tsochantaridis","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"989","DOI":"10.21437\/Interspeech.2011-406","article-title":"Structured support vector machines for noise robust continuous speech recognition","author":"zhang","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178777"},{"key":"ref16","article-title":"A comparison of training approaches for discriminative segmental models","author":"tang","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390205"},{"key":"ref18","article-title":"Hidden Markov support vector machines","author":"altun","year":"2003","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref19","first-page":"1169","article-title":"Learning structural svms with latent variables","author":"john yu","year":"0","journal-title":"Proceedings of the 26th Annual International Conference on Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178828"},{"key":"ref4","first-page":"1594","article-title":"Direct loss minimization for structured prediction","volume":"23","author":"hazan","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref27","first-page":"2729","article-title":"Hybrid mlp\/structured-svm tandem systems for large vocabulary and robust ASR","author":"ravuri","year":"2014","journal-title":"INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association"},{"article-title":"A log-linear discriminative modeling framework for speech recognition","year":"2010","author":"heigold","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.1005687"},{"key":"ref29","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"article-title":"Generalization bounds and consistency for structured labeling in predicting structured data","year":"2007","author":"mcallester","key":"ref5"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"10","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":"ref7","first-page":"2","article-title":"Hypothesis spaces for minimum bayes risk training in large vocabulary speech recognition","author":"gibson","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163908"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1169179"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0138"},{"key":"ref20","article-title":"The IBM 2015 english conversational telephone speech recognition system","volume":"abs 1505 5899","author":"saon","year":"2015","journal-title":"CoRR"},{"key":"ref22","article-title":"Language modeling in the icsi-sri spring 2005 meeting speech recognition evaluation system","author":"cetin","year":"2005","journal-title":"Tech Rep"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"journal-title":"Rt-04s evaluation data documentation","year":"0","key":"ref24"},{"journal-title":"Rt-2002 evaluation plan","year":"0","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638970"},{"journal-title":"Rt-05s evaluation data documentation","year":"0","key":"ref25"}],"event":{"name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","start":{"date-parts":[[2015,12,13]]},"location":"Scottsdale, AZ, USA","end":{"date-parts":[[2015,12,17]]}},"container-title":["2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7397480\/7404758\/07404771.pdf?arnumber=7404771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,3]],"date-time":"2022-06-03T21:23:46Z","timestamp":1654291426000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7404771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/asru.2015.7404771","relation":{},"subject":[],"published":{"date-parts":[[2015,12]]}}}