{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:27:31Z","timestamp":1749997651673,"version":"3.28.0"},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/asru.2017.8268931","type":"proceedings-article","created":{"date-parts":[[2018,1,25]],"date-time":"2018-01-25T21:43:53Z","timestamp":1516916633000},"page":"165-172","source":"Crossref","is-referenced-by-count":19,"title":["Lattice rescoring strategies for long short term memory language models in speech recognition"],"prefix":"10.1109","author":[{"given":"Shankar","family":"Kumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Nirschl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Holtmann-Rice","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hank","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ananda Theertha","family":"Suresh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1093"},{"journal-title":"Google preferred lineup explorer - YouTube","year":"0","key":"ref32"},{"key":"ref31","article-title":"Neu-ral speech recognizer: Acoustic-to-word LSTM model for large vocabulary speech recognition","author":"soltau","year":"2017","journal-title":"INTER-SPEECH IEEE"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.759736"},{"key":"ref36","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"ICML"},{"journal-title":"Improving Neural Networks with Dropout","year":"2013","author":"srivastava","key":"ref35"},{"key":"ref34","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"The Journal of Machine Learning Research"},{"key":"ref10","article-title":"Strate-gies for training large scale neural network language models","author":"mikolov","year":"2011","journal-title":"ASRU"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref13","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"hasim","year":"2014","journal-title":"TERSPEECH"},{"journal-title":"Generating Sequences with Recurrent Neural Networks","year":"2013","author":"graves","key":"ref14"},{"key":"ref15","first-page":"115","article-title":"Learning precise timing with LSTM recurrent networks","volume":"3","author":"gers","year":"2003","journal-title":"Journal of Machine Learning Research"},{"journal-title":"Tensorflow Large-scale machine learning on heterogeneous distributed systems","year":"2016","author":"martin","key":"ref16"},{"key":"ref17","article-title":"Hierarchical probabilistic neural network language model","author":"morin","year":"2005","journal-title":"AISTATS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854532"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.521"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.09.003"},{"journal-title":"Compressing deep convolutional networks using vector quantization","year":"2014","author":"gong","key":"ref27"},{"key":"ref3","first-page":"1137","article-title":"A neural probabilistic language model. 3: 1137–1155","volume":"3","author":"bengio","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2400218"},{"journal-title":"Fasttext zip Compressing text classification models","year":"2016","author":"joulin","key":"ref29"},{"key":"ref5","first-page":"20","article-title":"Deep neural network language models","author":"ebru","year":"2012","journal-title":"Proceedings of the NAACL-HLT 2012 Workshop Will We Ever Really Replace the N-gram Model? On the Future of Language Modeling for HLT"},{"key":"ref8","article-title":"Exploring the limits of language modeling","author":"josefowicz","year":"2016","journal-title":"arXiv preprint arXiv 1602 02410v2"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1438","DOI":"10.1109\/TASLP.2016.2558826","article-title":"Two efficient lattice rescoring methods using recurrent neural network language models","volume":"24","author":"xunying","year":"2016","journal-title":"IEEE Trans Audio Speech and Language Processing"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"InterSpeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1295"},{"journal-title":"Statistical Methods for Speech Recognition","year":"1997","author":"jelinek","key":"ref1"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"2146","DOI":"10.1109\/TASLP.2016.2598304","article-title":"Efficient training and evaluation of recurrent neural network language models for automatic speech recognition","volume":"24","author":"xie","year":"2016","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref22","article-title":"Joint language and translation modeling with recurrent neural networks","author":"auli","year":"2011","journal-title":"EMNLP"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1129"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/89.906002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1583"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164346"},{"key":"ref25","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"yonghui","year":"2016","journal-title":"CoRR"}],"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\/08268931.pdf?arnumber=8268931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T06:16:22Z","timestamp":1660371382000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8268931\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/asru.2017.8268931","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}