{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T23:35:48Z","timestamp":1772148948162,"version":"3.50.1"},"reference-count":67,"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":[{"DOI":"10.13039\/501100013290","name":"National Key Research and Development Program of China Stem Cell and Translational Research","doi-asserted-by":"publisher","award":["2018YFB1005003"],"award-info":[{"award-number":["2018YFB1005003"]}],"id":[{"id":"10.13039\/501100013290","id-type":"DOI","asserted-by":"publisher"}]},{"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, 61771472, 61773379"],"award-info":[{"award-number":["61901473, 61771472, 61773379"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Inria-CAS Joint Research Project","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.2021.3082299","type":"journal-article","created":{"date-parts":[[2021,5,20]],"date-time":"2021-05-20T19:49:28Z","timestamp":1621540168000},"page":"1897-1911","source":"Crossref","is-referenced-by-count":51,"title":["Fast End-to-End Speech Recognition Via Non-Autoregressive Models and Cross-Modal Knowledge Transferring From BERT"],"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":"Zhengkun","family":"Tian","sequence":"additional","affiliation":[]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Shuai","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1149"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013723"},{"key":"ref33","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1133"},{"key":"ref30","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume":"70","author":"gilmer","year":"0","journal-title":"Proc 34th Int Conf Machine Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015377"},{"key":"ref36","article-title":"Non-autoregressive neural machine translation","author":"gu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","article-title":"Fitnets: Hints for thin deep nets","author":"romero","year":"2014"},{"key":"ref34","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6301"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2933146"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref28","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","article-title":"Unsupervised pre-traing for sequence to sequence speech recognition","author":"fan","year":"2019"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053967"},{"key":"ref29","first-page":"10 881","article-title":"Graph Structure of Neural Networks","volume":"119","author":"you","year":"0","journal-title":"Proc 37th Int Conf Mach Learn Virtual Event ser Proc Machine Learn Res"},{"key":"ref66","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"zagoruyko","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref2","first-page":"99","author":"yu","year":"2016","journal-title":"Automatic Speech Recognition"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1554"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1600"},{"key":"ref24","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref26","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume":"70","author":"dauphin","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref25","article-title":"Transformers without tears: Improving the normalization of self-attention","author":"nguyen","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.348"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123369"},{"key":"ref59","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682539"},{"key":"ref57","article-title":"Aishell-2: Transforming mandarin asr research into industrial scale","author":"du","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref55","first-page":"8026","article-title":"Pytorch: An Imperative Style, High-Performance Deep Learning Library","volume":"32","author":"paszke","year":"0","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2759726"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3374754"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1437"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1107"},{"key":"ref12","first-page":"2837","article-title":"Online and linear-time attention by enforcing monotonic alignments","volume":"70","author":"raffel","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref13","article-title":"Monotonic Chunkwise Attention","author":"chiu","year":"0","journal-title":"Int Conf Lear Repres"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683510"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2928"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2203"},{"key":"ref17","first-page":"7884","article-title":"Synchronous transformers for end-to-end speech recognition","author":"tian","year":"0","journal-title":"Proc IEEE Int Conf Acoustics Speech Signal Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2341"},{"key":"ref19","first-page":"4171","article-title":"BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding","volume":"1","author":"devlin","year":"0","journal-title":"Proc 2019 Conf North Amer Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref3","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/860458.860459"},{"key":"ref7","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref46","first-page":"1081","article-title":"Effective sentence scoring method using bert for speech recognition","author":"shin","year":"0","journal-title":"Proc Asian Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref48","article-title":"A Model for Learning the Semantics of Pictures","volume":"1","author":"lavrenko","year":"2003","journal-title":"NIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1179"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref41","article-title":"Listen and fill in the missing letters: Non-autoregressive transformer for speech recognition","author":"chen","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref43","article-title":"On using monolingual corpora in neural machine translation","author":"gulcehre","year":"2015"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09437636.pdf?arnumber=9437636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:54:02Z","timestamp":1652194442000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9437636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3082299","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}