{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:42:54Z","timestamp":1730230974795,"version":"3.28.0"},"reference-count":34,"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\/icassp40776.2020.9053635","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7679-7683","source":"Crossref","is-referenced-by-count":5,"title":["Layer-Normalized LSTM for Hybrid-Hmm and End-To-End ASR"],"prefix":"10.1109","author":[{"given":"Mohammad","family":"Zeineldeen","sequence":"first","affiliation":[]},{"given":"Albert","family":"Zeyer","sequence":"additional","affiliation":[]},{"given":"Ralf","family":"Schluter","sequence":"additional","affiliation":[]},{"given":"Hermann","family":"Ney","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref30","article-title":"Rasr - the rwth aachen university open source speech recognition toolkit","author":"rybach","year":"2011","journal-title":"IEEE Automatic Speech Recognition and Understanding Workshop"},{"key":"ref34","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"USENIX Symp Operating Syst Design and Impl (OSDI 16)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","article-title":"Highway networks","volume":"abs 1505 387","author":"srivastava","year":"2015"},{"key":"ref12","article-title":"Layer normalization","volume":"abs 1607 6450","author":"ba","year":"2016"},{"key":"ref13","article-title":"Batch normalization: Accelerating deep network training by reducing internal co-variate shift","volume":"abs 1502 3167","author":"ioffe","year":"2015"},{"key":"ref14","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"NIPS"},{"key":"ref15","first-page":"3","article-title":"Group normalization","author":"wu","year":"2018","journal-title":"ECCV"},{"key":"ref16","article-title":"Recurrent batch normalization","volume":"abs 1603 9025","author":"cooijmans","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472159"},{"key":"ref18","first-page":"1942","article-title":"Batch renormalization: Towards reducing mini-batch dependence in batch-normalized models","author":"ioffe","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref19","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2225"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-4022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1176"},{"key":"ref27","article-title":"A comprehensive analysis on attention models","author":"zeyer","year":"2018","journal-title":"Interpretability and Robustness in Audio Speech and Language (IRASL) Workshop Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref6","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume":"28","author":"sutskever","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref29","first-page":"649","article-title":"Gammatone features and feature combination for large vocabulary speech recognition","author":"schl\u00fcter","year":"2007","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref7","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"key":"ref9","article-title":"Fixup initialization: Residual learning without normalization","volume":"abs 1901 9321","author":"zhang","year":"2019"},{"key":"ref1","first-page":"2462","article-title":"A comprehensive study of deep bidirectional lstm rnns for acoustic modeling in speech recognition","author":"zeyer","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"2411","DOI":"10.21437\/Interspeech.2017-556","article-title":"Dynamic layer normalization for adaptive neural acoustic modeling in speech recognition","author":"kim","year":"2017","journal-title":"InterSpeech"},{"article-title":"Gpu kernels for block-sparse weights","year":"2017","author":"gray","key":"ref21"},{"article-title":"Lossless data compression with neural networks","year":"2019","author":"bellard","key":"ref24"},{"key":"ref23","article-title":"Hypernetworks","volume":"abs 1609 9106","author":"ha","year":"2016","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1616"},{"key":"ref25","first-page":"517","article-title":"Switchboard: Telephone speech corpus for research and development","volume":"1","author":"godfrey","year":"2003","journal-title":"Proceedings of the 2003 IEEE International Conference on Acoustics Speech and Signal Processing"}],"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\/09053635.pdf?arnumber=9053635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:11:49Z","timestamp":1656375109000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053635","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}