{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T21:06:51Z","timestamp":1746479211417},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053264","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"6329-6333","source":"Crossref","is-referenced-by-count":12,"title":["Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks"],"prefix":"10.1109","author":[{"given":"A.","family":"Kastanos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A.","family":"Ragni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. J. F.","family":"Gales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953074"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"827","DOI":"10.21437\/Eurospeech.1997-281","article-title":"Estimating confidence using word lattices","author":"kemp","year":"1997","journal-title":"Eurospeech"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/89.906002"},{"key":"ref30","article-title":"Confidence measures in speech recognition based on probability distribution of likelihoods","author":"pinto","year":"2005","journal-title":"InterSpeech"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"key":"ref34","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":"ref10","first-page":"645","article-title":"Neural-network lexical translation for crosslingual IR from text and speech","author":"zbib","year":"2019","journal-title":"SIGIR"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1999-127","article-title":"Finding consensus among words: Lattice-based word error minimization","author":"mangu","year":"1999","journal-title":"Eurospeech"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.862067"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596078"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178922"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2819900"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639678"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683488"},{"key":"ref19","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref4","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"article-title":"Distributed representations of words and phrases and their compositionality","year":"2013","author":"mikolov","key":"ref27"},{"journal-title":"The HTK Book","year":"2015","author":"young","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.12.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0183"},{"article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326091"},{"key":"ref7","article-title":"Speaker adaptation using lattice-based MLLR","author":"uebel","year":"2001","journal-title":"ITRW"},{"key":"ref2","article-title":"Acoustic modeling for Google Home","author":"li","year":"2017","journal-title":"InterSpeech"},{"article-title":"Conversational AI: The science behind the Alexa prize","year":"2018","author":"ram","key":"ref1"},{"key":"ref9","article-title":"Using word lattice information for a tighter coupling in speech translation systems","author":"saleem","year":"2004","journal-title":"ICSLP"},{"key":"ref20","article-title":"Developing STT and KWS systems using limited language resources","author":"le","year":"2014","journal-title":"InterSpeech"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163916"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372916"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1649"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1583"},{"article-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"bahdanau","key":"ref26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053264.pdf?arnumber=9053264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T19:28:45Z","timestamp":1696015725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053264","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}