{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:27:00Z","timestamp":1730230020458,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461743","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"6104-6108","source":"Crossref","is-referenced-by-count":9,"title":["Prediction of LSTM-RNN Full Context States as a Subtask for N-Gram Feedforward Language Models"],"prefix":"10.1109","author":[{"given":"Kazuki","family":"Irie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihong","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ralf","family":"Schluter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hermann","family":"Ney","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref11","first-page":"1910","article-title":"Learning small-size DNN with output-distribution-based criteria","author":"li","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref12","first-page":"4825","article-title":"Knowledge distillation across ensembles of multilingual models for low-resource languages","author":"cui","year":"2017","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref13","first-page":"4820","article-title":"Knowledge distillation for small-footprint highway networks","author":"lu","year":"2017","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref14","first-page":"5275","article-title":"Student-teacher network learning with enhanced features","author":"watanabe","year":"2017","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-911"},{"key":"ref16","first-page":"3264","article-title":"Transferring knowledge from a RNN to a DNN","author":"chan","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref17","article-title":"Blending LSTMs into CNNs","author":"geras","year":"2016","journal-title":"International Conference on Learning Representations (ICLR) Workshop Track"},{"key":"ref18","first-page":"1317","article-title":"Sequence-level knowledge distillation","author":"kim","year":"2016","journal-title":"Proc Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref19","first-page":"1744","article-title":"Distilling an ensemble of greedy dependency parsers into one MST parser","author":"kuncoro","year":"2016","journal-title":"Proc Empirical Methods in Natural Language Processing (EMNLP)"},{"key":"ref4","article-title":"Investi-gation on log-linear interpolation of multi-domain neural network language model","author":"t\u00fcske","year":"2016","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref27","first-page":"661","article-title":"Lattice decoding and rescoring with long-span neural network language models","author":"sundermeyer","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"274","DOI":"10.21437\/Interspeech.2017-564","article-title":"Fast neural network language model lookups at n-gram speeds","author":"huang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref5","article-title":"Lan-guage modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc Int Conf on Machine Learning (ICML)"},{"key":"ref8","first-page":"2654","article-title":"Do deep nets really need to be deep?","volume":"27","author":"ba","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref7","first-page":"194","article-title":"LSTM neural networks for language modeling","author":"sundermeyer","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref2","first-page":"762","article-title":"Connectionist language modeling for large vocabulary continuous speech recognition","volume":"1","author":"schwenk","year":"2002","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref9","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2014","journal-title":"Deep Learning and Representation Learning Workshop NIPS"},{"key":"ref1","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref20","first-page":"5532","article-title":"Variational approximation of long-span language models for lvcsr","author":"deoras","year":"2011","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref22","first-page":"561","article-title":"Classes for fast maximum entropy training","volume":"1","author":"goodman","year":"2001","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.08.004"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1747","article-title":"Parallel neural network features for improved tandem acoustic modeling","author":"t\u00fcske","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"ref26","first-page":"2093","article-title":"rwthlm the RWTH Aachen University neural network language modeling toolkit","author":"sundermeyer","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref25","first-page":"221","article-title":"Forming word classes by statistical clustering for statistical language modelling","author":"kneser","year":"1991","journal-title":"Proc First Int Conf on Quantitative Linguistics (QUALICO)"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2018,4,15]]},"location":"Calgary, AB","end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08461743.pdf?arnumber=8461743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T22:28:33Z","timestamp":1598221713000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461743","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}