{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:06:53Z","timestamp":1730297213347,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023451","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:54:03Z","timestamp":1674827643000},"page":"331-338","source":"Crossref","is-referenced-by-count":0,"title":["Macro-Block Dropout for Improved Regularization in Training End-to-End Speech Recognition Models"],"prefix":"10.1109","author":[{"given":"Chanwoo","family":"Kim","sequence":"first","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sathish","family":"Indurti","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinhwan","family":"Park","sequence":"additional","affiliation":[{"name":"Samsung Research,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wonyong","family":"Sung","sequence":"additional","affiliation":[{"name":"Seoul National University,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF51394.2020.9443456"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1510"},{"key":"ref5","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Advances in Neural Information Processing Systems","volume":"28","author":"Chorowski","year":"2015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2024731"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/89.397090"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373233"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-157"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683514"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2020-49"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.07.006"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2545928"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462223"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-2566"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373230"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref18","first-page":"66","article-title":"Subword regularization: Improving neural net-work translation models with multiple subword candidates","volume-title":"Proceedings of the 56th Annual Meeting of the As-sociation for Computational Linguistics (Volume 1: Long Papers)","author":"Kudo"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461809"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054382"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414117"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"ref23","first-page":"93","article-title":"Generative adver-sarial network based acoustic scene training set augmentation and selection using svm hyper-plane","author":"Mun","year":"2017","journal-title":"DCASE"},{"key":"ref24","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"},{"issue":"3","key":"ref25","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","volume-title":"ser. Proceedings of Machine Learning Research","volume":"28","author":"Wan"},{"article-title":"Fractalnet: Ultra-deep neural networks without residuals","volume-title":"5th International Conference on Learning Representations, ICLR 2017","author":"Larsson","key":"ref26"},{"article-title":"Shake-shake regularization of 3-branch residual networks","volume-title":"5th International Conference on Learning Representations, ICLR 2017","author":"Gastaldi","key":"ref27"},{"key":"ref28","first-page":"10727","article-title":"Dropblock: A regularization method for convolutional networks","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Ghiasi","year":"2018"},{"key":"ref29","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Advances in Neural Information Processing Systems","volume":"25","author":"Krizhevsky","year":"2012"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639346"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2960566"},{"key":"ref32","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Gal","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404775"},{"key":"ref34","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Abadi"},{"volume-title":"Keras","year":"2015","author":"Chollet","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383157"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref38","first-page":"III-1310","article-title":"On the difficulty of training recurrent neural networks","volume-title":"Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28, ser. ICML13. JMLR.org","author":"Pascanu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2678162"},{"key":"ref40","first-page":"739","article-title":"Improved vocal tract length perturbation for a state-of-the-art end-to-end speech recognition system","volume-title":"INTERSPEECH-2019","author":"Kim"},{"key":"ref41","first-page":"5998","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003976"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, Conference Track Proceedings","author":"Kingma","year":"2015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003973"},{"volume-title":"Signal processing for robust speech recognition mo-tivated by auditory processing","year":"2010","author":"Kim","key":"ref46"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023451.pdf?arnumber=10023451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T01:21:44Z","timestamp":1710379304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023451\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023451","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}