{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:16Z","timestamp":1775229796007,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746979","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"6537-6541","source":"Crossref","is-referenced-by-count":8,"title":["Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition"],"prefix":"10.1109","author":[{"given":"Qiujia","family":"Li","sequence":"first","affiliation":[{"name":"University of Cambridge,UK"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"David","family":"Qiu","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Yanzhang","family":"He","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Liangliang","family":"Cao","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Philip C.","family":"Woodland","sequence":"additional","affiliation":[{"name":"University of Cambridge,UK"}]}],"member":"263","reference":[{"key":"ref38","article-title":"On calibration of modern neural networks","author":"guo","year":"2017","journal-title":"Proc ICML"},{"key":"ref33","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref32","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020","journal-title":"Proc NeurIPS SAS Workshop"},{"key":"ref31","article-title":"Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks","author":"rousseau","year":"2014","journal-title":"Proc LREC"},{"key":"ref30","article-title":"TED-LIUM 3: Twice as much data and corpus repartition for experiments on speaker adaptation","author":"hernandez","year":"2018","journal-title":"Proc Specom"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1997-282","article-title":"Improved estimation, evaluation and applications of confidence measures for speech recognition","author":"siu","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118432"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178922"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2819900"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639678"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683488"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413899"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-211"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3016"},{"key":"ref17","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Proc ICML Workshop on Representation Learning"},{"key":"ref18","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383570"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326091"},{"key":"ref27","article-title":"Can you trust your model’s uncertainty? Evaluating predictive uncertainty under dataset shift","author":"ovadia","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2141988"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.848882"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.08.002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0152"},{"key":"ref7","article-title":"Posterior probability decoding, confidence estimation and system combination","author":"evermann","year":"2000","journal-title":"Proc NIST Speech Transcription Workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.12.004"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.906002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-352"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2215"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413966"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414920"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-690"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3216"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2021-1207","article-title":"Multitask learning for end-to-end ASR word and utterance confidence with deletion prediction","author":"qiu","year":"2021","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688213"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746979.pdf?arnumber=9746979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:18:11Z","timestamp":1757096291000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746979\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746979","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}