{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:54:40Z","timestamp":1730199280502,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003850","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"807-813","source":"Crossref","is-referenced-by-count":1,"title":["Markov Recurrent Neural Network Language Model"],"prefix":"10.1109","author":[{"given":"Jen-Tzung","family":"Chien","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Che-Yu","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"ref33","first-page":"2635","article-title":"One billion word benchmark for measuring progress in statistical language modelling","author":"chelba","year":"2014","journal-title":"Proceedings of the Annual Conference of the International Communications Association"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424228"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683060"},{"journal-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","year":"2013","author":"bengio","key":"ref30"},{"journal-title":"Recur-rent neural network regularization","year":"2014","author":"zaremba","key":"ref37"},{"key":"ref36","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref35","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","author":"gal","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2428632"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-4006"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683771"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3332267"},{"key":"ref13","first-page":"3295","article-title":"A hierarchical latent variable encoder-decoder model for generating dialogues","author":"serban","year":"2017","journal-title":"Proc of AAAI Conference on Artificial Intelligence"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107295360"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2499302"},{"key":"ref16","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations"},{"key":"ref17","article-title":"Learning stochastic recurrent networks","author":"bayer","year":"2014","journal-title":"NIPS Advances in Variational Inference Workshop"},{"key":"ref18","first-page":"2980","article-title":"A recurrent latent variable model for sequential data","author":"chung","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"2199","article-title":"Sequential neural models with stochastic layers","author":"fraccaro","year":"2016","journal-title":"Advances in neural information processing systems"},{"journal-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"bahdanau","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1986.1165342"},{"key":"ref27","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"maddison","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/0301010"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2129911"},{"key":"ref8","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc of International Conference on Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1062"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2197156"},{"key":"ref9","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proceedings of the Annual Conference of the International Communications Association"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2173371"},{"key":"ref20","first-page":"6055","article-title":"Predictive state recurrent neural networks","author":"downey","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref22","article-title":"Skip RNN: Learning to skip state updates in recurrent neural networks","author":"campos","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref21","first-page":"1172","article-title":"Predictive-state decoders: Encoding the future into recurrent networks","author":"venkatraman","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2018.8517074"},{"key":"ref23","first-page":"201","article-title":"Latent Dirichlet language model for speech recognition","author":"chien","year":"2008","journal-title":"Proc of IEEE Spoken Language Technology Workshop"},{"key":"ref26","article-title":"Categorical reparameter-ization with Gumbel-softmax","author":"jang","year":"2017","journal-title":"International Conference on Learning Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-856"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2019,12,14]]},"location":"SG, Singapore","end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003850.pdf?arnumber=9003850","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:44:16Z","timestamp":1658155456000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003850\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003850","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}