{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T20:08:15Z","timestamp":1729627695062,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414920","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6388-6392","source":"Crossref","is-referenced-by-count":20,"title":["Confidence Estimation for Attention-Based Sequence-to-Sequence Models for Speech Recognition"],"prefix":"10.1109","author":[{"given":"Qiujia","family":"Li","sequence":"first","affiliation":[{"name":"University of Cambridge,UK"}]},{"given":"David","family":"Qiu","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Yanzhang","family":"He","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Philip C.","family":"Woodland","sequence":"additional","affiliation":[{"name":"University of Cambridge,UK"}]},{"given":"Liangliang","family":"Cao","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"Proc ICML Workshop on Representation Learning"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854010"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862067"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref30","article-title":"Practical variational inference for neural networks","author":"graves","year":"2011","journal-title":"Proc NIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003837"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref34","article-title":"On using monolingual corpora in neural machine translation","author":"gulcehre","year":"2015","journal-title":"ArXiv org 1503 03535"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-352","article-title":"Combining information sources for confidence estimation with CRF models","author":"seigel","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178922"},{"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\/ICASSP40776.2020.9053264"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref17","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2667"},{"key":"ref28","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326091"},{"key":"ref27","article-title":"Lingvo: A modular and scalable framework for sequence-to-sequence modeling","author":"shen","year":"2019","journal-title":"ArXiv org"},{"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\/CVPR.2016.308"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.08.002"},{"key":"ref8","article-title":"Posterior probability decoding, confidence estimation and system combination","author":"evermann","year":"2000","journal-title":"Proc NIST Speech Transcription Workshop"},{"key":"ref7","article-title":"Speaker adaptation using lattice-based MLLR","author":"uebel","year":"2001","journal-title":"Proc ITRW on Adaptation Methods for Speech Recognition"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.12.004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0152"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.906002"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref22","article-title":"On calibration of modern neural networks","author":"guo","year":"2017","journal-title":"Proc ICML"},{"key":"ref21","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"hendrycks","year":"2017","journal-title":"Proc ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"ref23","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289079"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414920.pdf?arnumber=9414920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:29:27Z","timestamp":1672129767000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414920","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}