{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T23:35:34Z","timestamp":1772148934548,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["2018YFB1005003"],"award-info":[{"award-number":["2018YFB1005003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61831022"],"award-info":[{"award-number":["61831022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61901473"],"award-info":[{"award-number":["61901473"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771472"],"award-info":[{"award-number":["61771472"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61773379"],"award-info":[{"award-number":["61773379"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Inria-CAS Joint Research","award":["173211KYSB20190049"],"award-info":[{"award-number":["173211KYSB20190049"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3066274","type":"journal-article","created":{"date-parts":[[2021,3,17]],"date-time":"2021-03-17T20:07:48Z","timestamp":1616011668000},"page":"1340-1351","source":"Crossref","is-referenced-by-count":8,"title":["Integrating Knowledge Into End-to-End Speech Recognition From External Text-Only Data"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5533-6909","authenticated-orcid":false,"given":"Ye","family":"Bai","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2422-4618","authenticated-orcid":false,"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Zhengkun","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Shuai","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref70","first-page":"8081","article-title":"Learning to specialize with knowledge distillation for visual question answering","author":"mun","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref38","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1177\/107769905303000401"},{"key":"ref32","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1554"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-519"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1539"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1096"},{"key":"ref60","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2225"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"},{"key":"ref63","first-page":"1826","article-title":"Adversarial regularization for attention based end-to-end robust speech recognition","volume":"27","author":"sun","year":"2019","journal-title":"IEEE Transactions on Audio"},{"key":"ref28","article-title":"Fitnets: Hints for thin deep nets","author":"romero","year":"2014"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref27","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref65","article-title":"Recent developments on espnet toolkit boosted by conformer","author":"guo","year":"0"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref29","first-page":"1910","article-title":"Learning small-size DNN with output-distribution-based criteria","author":"li","year":"0","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc"},{"key":"ref67","article-title":"Unsupervised pre-traing for sequence to sequence speech recognition","author":"fan","year":"2019"},{"key":"ref68","article-title":"Cat: Crf-based asr toolkit","author":"an","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2922048"},{"key":"ref2","first-page":"2345","article-title":"Sequence-discriminative training of deep neural networks","author":"vesel\u00fd","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref1","author":"yu","year":"2016","journal-title":"Automatic Speech Recognition"},{"key":"ref20","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume":"28","author":"bengio","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00256"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1160"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301443"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1046"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2935807"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-513"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1139"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref58","first-page":"220","article-title":"Intelligent selection of language model training data","author":"moore","year":"0","journal-title":"Proc ACL Conf Short Papers"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.2478\/pralin-2013-0013"},{"key":"ref56","first-page":"774","article-title":"Scalable term selection for text categorization","author":"li","year":"0","journal-title":"Proc Joint Conf Empirical Methods Nat Lang Process Comput Nat Lang Learn"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706600"},{"key":"ref54","article-title":"Aishell-2: Transforming mandarin asr research into industrial scale","author":"du","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref52","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"yang","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1345"},{"key":"ref12","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268935"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref15","first-page":"4171","article-title":"Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref16","article-title":"On using monolingual corpora in neural machine translation","author":"gulcehre","year":"0"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682490"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952599"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639347"},{"key":"ref6","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"3214","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"0","journal-title":"Proc 16th Annu Conf Int Speech Commun Assoc"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918423"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1073012.1073015"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620822"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179007"},{"key":"ref47","first-page":"876","article-title":"Learning trans-dimensional random fields with applications to language modeling","volume":"40","author":"wang","year":"2017"},{"key":"ref42","article-title":"Regularizing neural networks by penalizing confident output distributions","author":"pereyra","year":"2017","journal-title":"In International Conference on Learning Representations Workshop"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0159"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-343"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09380383.pdf?arnumber=9380383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:58Z","timestamp":1652194438000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9380383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3066274","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}