{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:03Z","timestamp":1774419363743,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890369","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Decoding for Efficient Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Xiangnan","family":"Ma","sequence":"first","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]},{"given":"Peizhuo","family":"Liu","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]},{"given":"Yuhao","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Shenzhen,China"}]},{"given":"Kaiqi","family":"Kou","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]},{"given":"Chenghao","family":"Gao","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]},{"given":"Tong","family":"Xiao","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]},{"given":"Jingbo","family":"Zhu","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Computer Science and Engineering,Shenyang,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1887"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref6","author":"Hinton","year":"2015","journal-title":"Distilling the knowledge in a neural network"},{"key":"ref7","volume-title":"A survey of quantization methods for efficient neural network inference","volume":"abs\/2103.13630","author":"Gholami","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1166"},{"key":"ref9","first-page":"16344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5220\/0010502000810086"},{"key":"ref12","first-page":"1302","article-title":"Efficient softmax approximation for gpus","volume-title":"International conference on machine learning","author":"Joulin"},{"key":"ref13","first-page":"5524","article-title":"Structured output layer neural network language model","volume-title":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Le"},{"key":"ref14","volume-title":"Efficient softmax approximation for gpus","volume":"abs\/1609.04309","author":"Grave","year":"2016"},{"key":"ref15","article-title":"Svd-softmax: Fast softmax approximation on large vocabulary neural networks","volume-title":"Neural Information Processing Systems","author":"Shim","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-483"},{"key":"ref19","author":"Jang","year":"2016","journal-title":"Categorical reparameterization with gumbel-softmax"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/11383-011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1168"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref26","first-page":"33","article-title":"Fairseq S2T: Fast speech-to-text modeling with fairseq","volume-title":"Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: System Demonstrations","author":"Wang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687874"},{"key":"ref28","first-page":"2","article-title":"Report on the 11th iwslt evaluation campaign","volume-title":"Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign","author":"Cettolo"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890369.pdf?arnumber=10890369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:30Z","timestamp":1774416150000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890369\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890369","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}