{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T23:02:22Z","timestamp":1784847742331,"version":"3.55.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688232","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"162-168","source":"Crossref","is-referenced-by-count":69,"title":["Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition"],"prefix":"10.1109","author":[{"given":"Xianrui","family":"Zheng","sequence":"first","affiliation":[{"name":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip C.","family":"Woodland","sequence":"additional","affiliation":[{"name":"Cambridge University,Engineering Dept.,Cambridge,U.K.,CB2 1PZ"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"On training bidirectional neural network language model with noise contrastive estimation","author":"he","year":"0","journal-title":"Proc ISCSLP"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179007"},{"key":"ref33","article-title":"Investigating bidirectional recurrent neural network language models for speech recognition","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref32","article-title":"Language models are few-shot learners","author":"brown","year":"0","journal-title":"Proc NIPS"},{"key":"ref31","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref30","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","author":"lan","year":"0","journal-title":"Proc ICLR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref34","article-title":"Layer normalization","author":"ba","year":"0","journal-title":"Proc NIPS"},{"key":"ref28","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","author":"yang","year":"0","journal-title":"Proc NIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref29","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/97.611282"},{"key":"ref1","author":"jelinek","year":"1997","journal-title":"Statistical Methods for Speech Recognition"},{"key":"ref20","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc NIPS"},{"key":"ref22","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018","journal-title":"OpenAIRE blog"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2225"},{"key":"ref24","article-title":"Universal language model finetuning for text classification","author":"howard","year":"0","journal-title":"Proc ACL"},{"key":"ref23","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"ArXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref25","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"liu","year":"2019","journal-title":"ArXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1873"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.09.003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-342"},{"key":"ref40","article-title":"Investigation on estimation of sentence probability by combining forward, backward and bidirectional LSTM-RNNs","author":"irie","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref12","article-title":"Structured output layer neural network language models for speech recognition","volume":"21","author":"le","year":"2013","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-65"},{"key":"ref16","article-title":"Regularizing and optimizing LSTM language models","author":"merity","year":"2017","journal-title":"ArXiv"},{"key":"ref17","article-title":"Comparison of feedforward and re-current neural network language models","author":"sundermeyer","year":"0","journal-title":"Proc ICASSP"},{"key":"ref18","article-title":"Neural turing machines","author":"graves","year":"2014","journal-title":"ArXiv"},{"key":"ref19","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1310"},{"key":"ref3","article-title":"Un-supervised adaptation of recurrent neural network language models","author":"gangireddy","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref6","article-title":"Effective sentence scoring method using BERT for speech recognition","author":"shin","year":"0","journal-title":"Proc ACML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.240"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053399"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383557"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref9","article-title":"A neural probabilistic language model","author":"bengio","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref46","article-title":"Combining frame-synchronous and label-synchronous systems for speech recognition","author":"li","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1683"},{"key":"ref48","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"paszke","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc ICLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462523"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref44","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc ASRU"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688232.pdf?arnumber=9688232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:47Z","timestamp":1652733707000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688232\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688232","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}