{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:42:06Z","timestamp":1730230926753,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096531","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Masked Token Similarity Transfer for Compressing Transformer-Based ASR Models"],"prefix":"10.1109","author":[{"given":"Euntae","family":"Choi","sequence":"first","affiliation":[{"name":"Seoul National University,Department of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youshin","family":"Lim","sequence":"additional","affiliation":[{"name":"42dot.ai,Hyundai Motor Company,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byeong-Yeol","family":"Kim","sequence":"additional","affiliation":[{"name":"42dot.ai,Hyundai Motor Company,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyung Yong","family":"Kim","sequence":"additional","affiliation":[{"name":"42dot.ai,Hyundai Motor Company,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanbin","family":"Lee","sequence":"additional","affiliation":[{"name":"42dot.ai,Hyundai Motor Company,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunkyu","family":"Lim","sequence":"additional","affiliation":[{"name":"42dot.ai,Hyundai Motor Company,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seung Woo","family":"Yu","sequence":"additional","affiliation":[{"name":"42dot.ai,Hyundai Motor Company,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungjoo","family":"Yoo","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of Computer Science and Engineering"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv preprint arXiv 1607 06450"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.21437\/Interspeech.2022-11112"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref15","article-title":"Understanding the role of self attention for efficient speech recognition","author":"shim","year":"2022","journal-title":"International Conference on Learning Representations"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.21437\/Interspeech.2022-11034"},{"key":"ref20","article-title":"Reducing transformer depth on demand with structured dropout","author":"fan","year":"2020","journal-title":"International Conference on Learning Representations"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLR (Poster)"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.18653\/v1\/D19-1441"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref2","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"grill","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref1","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1007\/978-3-031-19790-1_16"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.21437\/Interspeech.2022-422"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.18653\/v1\/N19-4009"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref8","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Volume 1 (Long and Short Papers)"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref9","article-title":"Distilling the knowledge in a neural network","volume":"2","author":"hinton","year":"2015","journal-title":"arXiv preprint arXiv 1503 02531"},{"key":"ref4","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.21437\/Interspeech.2019-1873"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1145\/1143844.1143891"},{"key":"ref5","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096531.pdf?arnumber=10096531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:57:55Z","timestamp":1700506675000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096531\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096531","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}