{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:47:03Z","timestamp":1776883623990,"version":"3.51.2"},"reference-count":41,"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\/slt54892.2023.10022960","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"152-159","source":"Crossref","is-referenced-by-count":8,"title":["Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-to-End Automatic Speech Recognition"],"prefix":"10.1109","author":[{"given":"Aleksandr","family":"Laptev","sequence":"first","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris","family":"Ginsburg","sequence":"additional","affiliation":[{"name":"NVIDIA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707741"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.848882"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.03.004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1382"},{"key":"ref5","article-title":"Speaker adaptation using lattice-based MLLR","author":"Uebel","year":"2001","journal-title":"ITRW"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331222"},{"key":"ref7","article-title":"Using word lattice information for a tighter coupling in speech translation systems","author":"Saleem","year":"2004","journal-title":"ICSLP"},{"key":"ref8","article-title":"Word confidence estimation for speech translation","volume-title":"International Workshop on Spoken Language Translation","author":"Besacier","year":"2014"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/89.906002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.12.004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2141988"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref13","article-title":"Sequence transduction with recurrent neural networks","volume-title":"ICML","author":"Graves","year":"2012"},{"key":"ref14","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"Hendrycks","year":"2016","journal-title":"ICLR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683086"},{"key":"ref18","article-title":"Uncertainty estimation in autoregressive structured prediction","volume-title":"ICLR","author":"Malinin","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/slt48900.2021.9383570"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414920"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053287"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2215"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413966"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-690"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1207"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688247"},{"key":"ref27","first-page":"78","article-title":"Posterior probability decoding, confidence estimation and system combination","volume-title":"NIST Speech Transcription Workshop","volume":"27","author":"Evermann"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2667"},{"key":"ref29","article-title":"NeMo: a toolkit for building AI applications using neural modules","author":"Kuchaiev","year":"2019","journal-title":"arXiv:1909.09577"},{"issue":"4","key":"ref30","first-page":"383","article-title":"Entropy methods for the confidence assessment of probabilistic classification models","volume":"81","author":"Tornetta","year":"2021","journal-title":"Statistica"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2022.3147187"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF01016429"},{"key":"ref33","article-title":"Distilling the knowledge in a neural network","volume-title":"NIPS Deep Learning and Representation Learning Workshop","author":"Hinton","year":"2015"},{"key":"ref34","first-page":"547","article-title":"On measures of entropy and information","volume-title":"Proceedings of the fourth Berkeley symposium on mathematical statistics and probability","volume":"1","author":"R\u00e9nyi"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502245"},{"key":"ref38","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015","journal-title":"arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-282"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9602"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3"}],"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\/10022960.pdf?arnumber=10022960","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:36:24Z","timestamp":1707806184000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022960\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022960","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}