{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:38Z","timestamp":1760245058879,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053573","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7839-7843","source":"Crossref","is-referenced-by-count":21,"title":["The Rwth Asr System for Ted-Lium Release 2: Improving Hybrid Hmm With Specaugment"],"prefix":"10.1109","author":[{"given":"Wei","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Wilfried","family":"Michel","sequence":"additional","affiliation":[]},{"given":"Kazuki","family":"Irie","sequence":"additional","affiliation":[]},{"given":"Markus","family":"Kitza","sequence":"additional","affiliation":[]},{"given":"Ralf","family":"Schluter","sequence":"additional","affiliation":[]},{"given":"Hermann","family":"Ney","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref10","article-title":"SpecAugment: A Simple Augmentation Method for Automatic Speech Recognition","author":"zoph","year":"2019","journal-title":"InterSpeech"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref13","article-title":"On Using SpecAugment for End-to-End Speech Translation","author":"bahar","year":"2019","journal-title":"International Workshop on Spoken Language Translation"},{"key":"ref14","first-page":"26","article-title":"Enhancing the TED-LIUM Corpus with Selected Data for Language Modeling and More TED Talks","author":"rousseau","year":"2014","journal-title":"Proc LREC"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953177"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854207"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2015"},{"article-title":"Incorporating Nesterov Momentum into Adam","year":"2016","author":"dozat","key":"ref18"},{"key":"ref19","first-page":"153","article-title":"Greedy Layer-Wise Training of Deep Networks","volume":"19","author":"bengio","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1999.0128"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479394"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2162"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"194","DOI":"10.21437\/Interspeech.2012-65","article-title":"LSTM Neural Networks for Language Modeling","author":"sundermeyer","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"1433","DOI":"10.21437\/Interspeech.2011-250","article-title":"On the Estimation of Discount Parameters for Language Model Smoothing","author":"sundermeyer","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-603","article-title":"Hypothesis Spaces for Minimum Bayes Risk Training in Large Vocabulary Speech Recognition","author":"gibson","year":"2006","journal-title":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2225"},{"key":"ref7","first-page":"5998","article-title":"Attention Is All You Need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"article-title":"LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring","year":"2019","author":"beck","key":"ref9"},{"journal-title":"Connectionist Speech Recognition A Hybrid Approach","year":"1993","author":"bourlard","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952599"},{"key":"ref22","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref24","article-title":"The CAPIO 2017 Conversational Speech Recognition System","author":"han","year":"2018","journal-title":"ArXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1973"},{"key":"ref26","article-title":"How Much Self-attention Do We Need? Trading Attention for Feed-forward Layers","author":"irie","year":"2020","journal-title":"ICASSP"},{"key":"ref25","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053573.pdf?arnumber=9053573","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:28:40Z","timestamp":1696015720000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053573\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053573","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}