{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:27:45Z","timestamp":1776889665038,"version":"3.51.2"},"reference-count":27,"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\/slt54892.2023.10022581","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"280-286","source":"Crossref","is-referenced-by-count":9,"title":["Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Ji Won","family":"Yoon","sequence":"first","affiliation":[{"name":"Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beom Jun","family":"Woo","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunghwan","family":"Ahn","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyeonseung","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nam Soo","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Department of ECE and INMC,Seoul,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","article-title":"Deeply-supervised nets","volume-title":"Proc. AISTATS","author":"Lee"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref4","first-page":"5206","article-title":"Librispeech: an asr corpus based on public domain au-dio books","volume-title":"Proc. ICASSP","author":"Panayotov"},{"key":"ref5","article-title":"Imputer: sequence modelling via imputation and dynamic programming","volume-title":"Proc. ICML","author":"Chan"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref7","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 preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053889"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref10","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS Work-shop Deep Learn.","author":"Hinton"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-432"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1190"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953163"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953072"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-614"},{"key":"ref16","article-title":"Blending lstms into cnns","volume-title":"Proc. ICLR Workshop","author":"Geras"},{"key":"ref17","first-page":"604","article-title":"Acoustic modelling with cd-ctc-smbr lstm rnns","volume-title":"Proc. ASRU","author":"Senior"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8461995"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8682671"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/slt.2018.8639629"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1952"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3071662"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1819"},{"key":"ref25","article-title":"Mixed-precision training for nlp and speech recognition with openseq2seq","author":"Kuchaiev","year":"2018","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Stochastic gradient methods with layer-wise adaptive moments for training of deep networks","author":"Ginsburg","year":"2019","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Kenlm: faster and smaller language model queries","volume-title":"Proc. EMNLP","author":"Heafield"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"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\/10022581.pdf?arnumber=10022581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T08:07:13Z","timestamp":1707811633000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022581","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}