{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:27Z","timestamp":1760245047106,"version":"3.41.0"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/asru.2015.7404786","type":"proceedings-article","created":{"date-parts":[[2016,2,12]],"date-time":"2016-02-12T13:55:42Z","timestamp":1455285342000},"page":"137-144","source":"Crossref","is-referenced-by-count":5,"title":["Towards structured deep neural network for automatic speech recognition"],"prefix":"10.1109","author":[{"given":"Yi-Hsiu","family":"Liao","sequence":"first","affiliation":[]},{"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Lin-shan","family":"Lee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","year":"2001","author":"lafferty","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119206"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.21437\/Interspeech.2005-126","article-title":"Hidden conditional random fields for phone classification","author":"gunawardana","year":"2005","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372916"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373329"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"2986","DOI":"10.21437\/Interspeech.2010-35","article-title":"Deep-structured hidden conditional random fields for phonetic recognition","author":"yu","year":"2010","journal-title":"InterSpeech"},{"key":"ref16","first-page":"1453","article-title":"Large margin methods for structured and interdependent output variables","author":"tsochantaridis","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","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":"InterSpeech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2227734"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495097"},{"article-title":"struct svm, support vector machine for complex outputs","year":"2008","author":"joachims","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/29.46546"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref6","article-title":"Acoustic modeling with deep neural networks using raw time signal for lvcsr","author":"t\u00fcske","year":"2014","journal-title":"Proceedings of the Annual Conference of International Speech Communication Association (INTERSPEECH)"},{"key":"ref29","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495662"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"114","DOI":"10.21437\/Interspeech.2013-49","article-title":"Deep vs. wide: depth on a budget for robust speech recognition","author":"vinyals","year":"2013","journal-title":"InterSpeech"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Science"},{"key":"ref9","volume":"14","author":"rabiner","year":"1993","journal-title":"Fundamentals of speech recognition"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130401"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-14","article-title":"Integrating deep neural networks into structural classification approach based on weighted finite-state transducers","author":"kubo","year":"2012","journal-title":"InterSpeech"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178777"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/72.554195"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5108-8"},{"key":"ref26","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref25","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"}],"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\/07404786.pdf?arnumber=7404786","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T10:58:06Z","timestamp":1748775486000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7404786\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/asru.2015.7404786","relation":{},"subject":[],"published":{"date-parts":[[2015,12]]}}}