{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T08:41:40Z","timestamp":1776156100463,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100006355","name":"Shun Hing Institute of Advanced Engineering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006355","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414046","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7378-7382","source":"Crossref","is-referenced-by-count":15,"title":["Bayesian Transformer Language Models for Speech Recognition"],"prefix":"10.1109","author":[{"given":"Boyang","family":"Xue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhao","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shansong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoukang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zi","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengzhe","family":"Geng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref10","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref11","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"ICML"},{"key":"ref12","article-title":"An empirical study of transformer-based neural language model adaptation","author":"li","year":"2020","journal-title":"ICASSP"},{"key":"ref13","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2499302"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683660"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1927"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-51"},{"key":"ref18","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"2015","journal-title":"ICML"},{"key":"ref19","first-page":"14660","article-title":"Bayesian layers: A module for neural network uncertainty","author":"tran","year":"2019","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref28","article-title":"Development of the cuhk elderly speech recognition system for neurocognitive disorder detection using the dementiabank corpus","author":"ye","year":"2021","journal-title":"ICASSP"},{"key":"ref4","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref27","article-title":"Variational dropout and the local reparameterization trick","author":"kingma","year":"2015","journal-title":"Computer Science"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1053"},{"key":"ref29","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2225"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"key":"ref7","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"CoRR"},{"key":"ref2","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2015","journal-title":"InterSpeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078569"},{"key":"ref22","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref21","article-title":"Blt: Exact bayesian inference with distribution transformers","author":"yuan","year":"0"},{"key":"ref24","first-page":"215","article-title":"Ensemble learning in bayesian neural networks","volume":"168","author":"barber","year":"1998","journal-title":"NATO ASI Series F Computer and Systems Sciences"},{"key":"ref23","article-title":"Bridging nonlinearities and stochastic regularizers with gaussian error linear units","author":"hendrycks","year":"2016","journal-title":"CoRR"},{"key":"ref26","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013"},{"key":"ref25","first-page":"2348","article-title":"Practical variational inference for neural networks","author":"graves","year":"2011","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414046.pdf?arnumber=9414046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:58Z","timestamp":1652197258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414046","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}