{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T06:33:18Z","timestamp":1723789998745},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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\/icassp39728.2021.9413966","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"source":"Crossref","is-referenced-by-count":14,"title":["Learning Word-Level Confidence for Subword End-To-End ASR"],"prefix":"10.1109","author":[{"given":"David","family":"Qiu","sequence":"first","affiliation":[]},{"given":"Qiujia","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yanzhang","family":"He","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[]},{"given":"Liangliang","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[]},{"given":"Deepti","family":"Bhatia","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ke","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[]},{"given":"Ian","family":"McGraw","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","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":"Eurospeech"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-264"},{"key":"ref33","article-title":"Lingvo: A modular and scalable framework for sequence-to-sequence modeling","author":"shen","year":"2019","journal-title":"arXiv 1902 08295"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288828"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.170"},{"key":"ref30","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref37","article-title":"Improving wide-band speech recognition using mixed-bandwidth training data in CD-DNN-HMM","author":"li","year":"2012","journal-title":"SLT"},{"key":"ref36","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1510","article-title":"Generation of large-scale simulated utterances in virtual rooms to train deep-neural networks for far-field speech recognition in Google Home","author":"kim","year":"2017","journal-title":"InterSpeech"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref34","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0152"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-275"},{"key":"ref11","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":"InterSpeech"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178922"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639678"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1241"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683488"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054188"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053896"},{"key":"ref28","article-title":"Confidence estimation for attention-based sequence-to-sequence models for speech recognition","author":"li","year":"2020","journal-title":"arXiv 2010 11428"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326091"},{"key":"ref27","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"NIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2141988"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref29","article-title":"Deliberation model based two-pass end-to-end speech recognition","author":"hu","year":"2020","journal-title":"ICASSP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.08.002"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref7","article-title":"Posterior probability decoding, confidence estimation and system combination","author":"evermann","year":"2000","journal-title":"NIST Speech Transcription Workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.12.004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862067"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/89.906002"},{"key":"ref20","article-title":"Transformer-transducer: End-to-end speech recognition with self-attention","author":"yeh","year":"2019","journal-title":"arXiv 1910 12977"},{"key":"ref22","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref24","article-title":"On calibration of modern neural networks","author":"guo","year":"2017","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2875"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-343"},{"key":"ref25","article-title":"Can you trust your model’s uncertainty? Evaluating predictive uncertainty under dataset shift","author":"ovadia","year":"2019","journal-title":"NeurIPS"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"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\/09413966.pdf?arnumber=9413966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T08:31:01Z","timestamp":1672129861000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413966\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413966","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}