{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:23:01Z","timestamp":1740169381721,"version":"3.37.3"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Chung-Ang University Research Grants in 2024"},{"DOI":"10.13039\/100004358","name":"Samsung","doi-asserted-by":"publisher","award":["IO201211-08075-01"],"id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3457859","type":"journal-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T18:37:31Z","timestamp":1726079851000},"page":"131136-131146","source":"Crossref","is-referenced-by-count":0,"title":["Cons-KD: Dropout-Robust Knowledge Distillation for CTC-Based Automatic Speech Recognition"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8631-4489","authenticated-orcid":false,"given":"Ji","family":"Won Yoon","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Chung-Ang University, Seoul, South Korea"}]},{"given":"Hyeonseung","family":"Lee","sequence":"additional","affiliation":[{"name":"XL8 Inc., Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9652-648X","authenticated-orcid":false,"given":"Ju","family":"Yeon Kang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0568-4902","authenticated-orcid":false,"given":"Nam","family":"Soo Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref4","first-page":"1","article-title":"Sequence transduction with recurrent neural networks","volume-title":"Proc. ICML Workshop Represent. Learn.","author":"Graves"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"ref6","article-title":"Citrinet: Closing the gap between non-autoregressive and autoregressive end-to-end models for automatic speech recognition","author":"Majumdar","year":"2021","journal-title":"arXiv:2104.01721"},{"key":"ref7","first-page":"1","article-title":"Carnelinet: Neural mixture model for automatic speech recognition","volume-title":"Proc. ASRU","author":"Kalinov"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref9","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS Workshop Deep Learn.","author":"Hinton"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3071662"},{"key":"ref11","first-page":"1","article-title":"Inter-KD: Intermediate knowledge distillation for CTC-based automatic speech recognition","volume-title":"Proc. IEEE Spoken Language Technology Workshop","author":"Yoon"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1952"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639629"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461995"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682671"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404851"},{"key":"ref17","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"JMLR"},{"key":"ref18","first-page":"1","article-title":"Dropout with expectation-linear regularization","volume-title":"Proc. ICLR","author":"Ma"},{"key":"ref19","first-page":"1","article-title":"Fraternal dropout","volume-title":"Proc. ICLR","author":"Zolna"},{"key":"ref20","first-page":"1","article-title":"R-drop: Regularized dropout for neural networks","volume-title":"Proc. NIPS","author":"Liang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-432"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953163"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953072"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-614"},{"key":"ref26","first-page":"1","article-title":"Blending LSTMs into CNNs","volume-title":"Proc. ICLR Workshop","author":"Geras"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref28","first-page":"1","article-title":"Fitnets: Hints for thin deep nets","volume-title":"Proc. ICLR","author":"Romero"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref31","first-page":"4211","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proc. LREC","author":"Ardila"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446861"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref34","article-title":"NeMo: A toolkit for building AI applications using neural modules","author":"Kuchaiev","year":"2019","journal-title":"arXiv:1909.09577"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref36","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref38","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"162","author":"Baevski"},{"key":"ref39","article-title":"Efficient self-supervised learning with contextualized target representations for vision, speech and language","author":"Baevski","year":"2022","journal-title":"arXiv:2212.07525"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref41","first-page":"1","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","volume-title":"Proc. NIPS","author":"Grill"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref43","first-page":"1","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. NIPS","author":"Tarvainen"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10676954.pdf?arnumber=10676954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T19:29:08Z","timestamp":1727292548000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10676954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3457859","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}