{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:04:46Z","timestamp":1775199886222,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434678","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid Decoding: Rapid Pass and Selective Detailed Correction for Sequence Models"],"prefix":"10.1109","author":[{"given":"Yunkyu","family":"Lim","sequence":"first","affiliation":[{"name":"42dot Inc.,,Republic of Korea"}]},{"given":"Jihwan","family":"Park","sequence":"additional","affiliation":[{"name":"42dot Inc.,,Republic of Korea"}]},{"given":"Hyung Yong","family":"Kim","sequence":"additional","affiliation":[{"name":"42dot Inc.,,Republic of Korea"}]},{"given":"Hanbin","family":"Lee","sequence":"additional","affiliation":[{"name":"42dot Inc.,,Republic of Korea"}]},{"given":"Byeong-Yeol","family":"Kim","sequence":"additional","affiliation":[{"name":"42dot Inc.,,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2015","journal-title":"ICLR."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-14596-5_12"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref5","article-title":"Sequence transduction with recurrent neural networks","volume-title":"Internation Conference on Machine Learning (ICML) Workshop on Representation Learning.","author":"Graves"},{"key":"ref6","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"issue":"05101","key":"ref8","article-title":"CR-CTC: Consistency regularization on CTC for improved speech recognition","author":"Yao","year":"2024","journal-title":"arXiv preprint arXiv:2410"},{"key":"ref9","first-page":"38462","article-title":"Efficient sequence transduction by jointly predicting tokens and durations","volume-title":"International Conference on Machine Learning","author":"Xu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023214"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2323"},{"issue":"2020","key":"ref12","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","journal-title":"Advances in neural information processing systems"},{"issue":"13979","key":"ref13","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"Conneau","year":"2020","journal-title":"arXiv preprint arXiv:2006"},{"key":"ref14","first-page":"28492","article-title":"Robust speech recognition via largescale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"05931","key":"ref15","article-title":"Training and Inference Efficiency of Encoder-Decoder Speech Models","author":"\u017belasko","year":"2025","journal-title":"arXiv preprint arXiv:2503"},{"key":"ref16","article-title":"Distil-whisper: Robust knowledge distillation via large-scale pseudo labelling","author":"Gandhi","year":"2023","journal-title":"arXiv:2311.00430."},{"key":"ref17","first-page":"19274","article-title":"Fast inference from transformers via speculative decoding","volume-title":"International Conference on Machine Learning","author":"Leviathan"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461809"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref21","article-title":"NeMo: a toolkit for Conversational AI and Large Language Models","author":"Harper"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434678.pdf?arnumber=11434678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:09Z","timestamp":1775192289000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434678","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}