{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:46:11Z","timestamp":1767084371859,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683533","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"7230-7234","source":"Crossref","is-referenced-by-count":14,"title":["Knowledge Distillation for Recurrent Neural Network Language Modeling with Trust Regularization"],"prefix":"10.1109","author":[{"given":"Yangyang","family":"Shi","sequence":"first","affiliation":[]},{"given":"Mei-Yuh","family":"Hwang","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Lei","sequence":"additional","affiliation":[]},{"given":"Haoyu","family":"Sheng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Breaking the Softmax Bottleneck: A High-Rank RNN Language Model","volume":"arxiv 1711 3953","author":"yang","year":"2017","journal-title":"CoRR"},{"key":"ref11","article-title":"Regularizing and Optimizing LSTM Language Models","volume":"arxiv 1708 2182","author":"merity","year":"2017","journal-title":"CoRR"},{"key":"ref12","article-title":"Recurrent Neural Network Regularization","volume":"arxiv 1409 2329","author":"zaremba","year":"2014","journal-title":"CoRR"},{"key":"ref13","first-page":"109","article-title":"Regularization of neural networks using dropconnect","author":"wan","year":"2013","journal-title":"Machine Learning Research"},{"key":"ref14","article-title":"A Theoretically Grounded Application of Dropout in Recurrent Neural Networks","volume":"arxiv 1512 5287","author":"gal","year":"2015","journal-title":"CoRR"},{"key":"ref15","article-title":"FitNets: Hints for Thin Deep Nets","volume":"arxiv 1412 6550","author":"romero","year":"2014","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/SLT.2012.6424228"},{"key":"ref17","article-title":"Character-Aware Neural Language Models","volume":"arxiv 1508 6615","author":"kim","year":"2015","journal-title":"CoRR"},{"key":"ref18","article-title":"Pointer Sentinel Mixture Models","volume":"arxiv 1609 7843","author":"merity","year":"2016","journal-title":"CoRR"},{"key":"ref19","article-title":"Improving Neural Language Models with a Continuous Cache","volume":"arxiv 1612 4426","author":"grave","year":"2016","journal-title":"CoRR"},{"key":"ref4","article-title":"Predicting Parameters in Deep Learning","author":"denil","year":"2013","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.18653\/v1\/D15-1044"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.18653\/v1\/K16-1029"},{"key":"ref5","first-page":"2849","article-title":"Fixed Point Quantization of Deep Convolutional Networks","volume":"48","author":"lin","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref8","article-title":"Distilling the Knowledge in a Neural Network","volume":"arxiv 1503 2531","author":"hinton","year":"2015","journal-title":"CoRR"},{"key":"ref7","article-title":"Restructuring of deep neural network acoustic models with singular value decomposition","author":"xue","year":"2013","journal-title":"The Proceedings of Interspeech"},{"key":"ref2","first-page":"11","article-title":"Large, Pruned or Continuous Space Language Models on a GPU for Statistical Machine Translation","author":"schwenk","year":"2012","journal-title":"Proc NAACL-HLT Workshop Future Lang Model for HLT"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.3115\/1075527.1075614"},{"key":"ref1","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":"The Proceedings of Interspeech"},{"key":"ref20","article-title":"Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling","volume":"arxiv 1611 1462","author":"inan","year":"2016","journal-title":"CoRR"},{"key":"ref22","article-title":"Neural Architecture Search with Reinforcement Learning","volume":"arxiv 1611 1578","author":"zoph","year":"2016","journal-title":"CoRR"},{"key":"ref21","article-title":"Recurrent Highway Networks","volume":"arxiv 1607 3474","author":"zilly","year":"2016","journal-title":"CoRR"},{"key":"ref24","article-title":"Regularizing and Optimizing LSTM Language Models","volume":"arxiv 1708 2182","author":"merity","year":"2017","journal-title":"CoRR"},{"key":"ref23","article-title":"On the State of the Art of Evaluation in Neural Language Models","volume":"arxiv 1707 5589","author":"melis","year":"2017","journal-title":"CoRR"},{"key":"ref25","first-page":"1","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"Proc of ASRU '"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683533.pdf?arnumber=8683533","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T05:33:58Z","timestamp":1663306438000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683533\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683533","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}