{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:36:03Z","timestamp":1766136963289},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/asru.2017.8268942","type":"proceedings-article","created":{"date-parts":[[2018,1,25]],"date-time":"2018-01-25T21:43:53Z","timestamp":1516916633000},"page":"244-251","source":"Crossref","is-referenced-by-count":22,"title":["Language modeling with highway LSTM"],"prefix":"10.1109","author":[{"given":"Gakuto","family":"Kurata","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Saon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Sethy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1544"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953159"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266481"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1460"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-491"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-405"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-723"},{"journal-title":"Highway networks","year":"2015","author":"srivastava","key":"ref12"},{"journal-title":"Character-Aware Neural Language Models","year":"2015","author":"kim","key":"ref13"},{"key":"ref14","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"Proc NIPS"},{"journal-title":"Generating Sequences with Recurrent Neural Networks","year":"2013","author":"graves","key":"ref15"},{"key":"ref16","first-page":"2342","article-title":"An empirical exploration of recurrent network architectures","author":"jozefowicz","year":"2015","journal-title":"Proc ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"journal-title":"Language Modeling with Gated Convolutional Networks[J]","year":"2016","author":"dauphin","key":"ref18"},{"journal-title":"Adam A method for stochastic optimization","year":"2014","author":"kingma","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620822"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620820"},{"journal-title":"Achieving human parity in conversational speech recognition","year":"2016","author":"xiong","key":"ref3"},{"journal-title":"How to construct deep recurrent neural networks","year":"2013","author":"pascanu","key":"ref6"},{"key":"ref29","article-title":"Scaling shrinkage-based language models","author":"chen","year":"2010","journal-title":"IBM Research Report RC24970"},{"key":"ref5","first-page":"1044","article-title":"Joint language and translation modeling with recurrent neural networks","author":"auli","year":"2013","journal-title":"Proc EMNLP"},{"journal-title":"Fast-slow recurrent neural networks","year":"2017","author":"mujika","key":"ref8"},{"journal-title":"Recurrent highway networks","year":"2016","author":"zilly","key":"ref7"},{"journal-title":"Exploring the limits of language modeling","year":"2016","author":"jozefowicz","key":"ref2"},{"journal-title":"The Microsoft 2017 conversational speech recognition system","year":"2017","author":"xiong","key":"ref9"},{"journal-title":"Recurrent Neural Network Regularization","year":"2014","author":"zaremba","key":"ref1"},{"journal-title":"Layer normalization","year":"2016","author":"ba","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.879814"},{"key":"ref24","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960445"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1999.0128"}],"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\/08268942.pdf?arnumber=8268942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T06:19:41Z","timestamp":1660371581000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8268942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/asru.2017.8268942","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}