{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:18:56Z","timestamp":1792786736813,"version":"4.5.0"},"reference-count":58,"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\/501100001868","name":"National Science Council","doi-asserted-by":"publisher","award":["110-2628-E-002-001"],"award-info":[{"award-number":["110-2628-E-002-001"]}],"id":[{"id":"10.13039\/501100001868","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006477","name":"National Taiwan University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006477","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ASUS AICS"}],"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.2021.3095662","type":"journal-article","created":{"date-parts":[[2021,7,8]],"date-time":"2021-07-08T15:48:01Z","timestamp":1625759281000},"page":"2351-2366","source":"Crossref","is-referenced-by-count":235,"title":["TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2502-3992","authenticated-orcid":false,"given":"Andy T.","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0656-9874","authenticated-orcid":false,"given":"Shang-Wen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9654-5747","authenticated-orcid":false,"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2026"},{"key":"ref38","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"yang","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref33","article-title":"A Robustly Optimized BERT Pretraining Approach","author":"liu","year":"0"},{"key":"ref32","first-page":"4171","article-title":"Pre-Training of Deep Bidirectional Transformers for Language Understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Human Lang Technol"},{"key":"ref31","article-title":"The S3PRL Toolkit: Self-Supervised Speech Pre-Training and Representation Learning","author":"liu","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1213"},{"key":"ref37","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"lan","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref35","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref28","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref27","article-title":"Non-Autoregressive Predictive Coding for Learning Speech Representations From Local Dependencies","author":"liu","year":"2020"},{"key":"ref29","first-page":"194","article-title":"How to fine-tune bert for text classification?","volume":"11856","author":"sun","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref1","article-title":"Representation Learning With Contrastive Predictive Coding","author":"oord","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053541"},{"key":"ref21","first-page":"344","article-title":"Audio albert: A lite bert for self-supervised learning of audio representation","author":"chi","year":"2020","journal-title":"Proc IEEE Spoken Lang Technol Workshop"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2007"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1511"},{"key":"ref26","article-title":"Masked Pre-Trained Encoder Base on Joint Ctc-Transformer","author":"liu","year":"2020"},{"key":"ref25","first-page":"6538","article-title":"A further study of unsupervised pre-training for transformer based speech recognition","author":"jiang","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref50","first-page":"285","article-title":"Phone recognition on the timit database","volume":"1","author":"lopes","year":"2011","journal-title":"Speech Technol \/Book"},{"key":"ref51","article-title":"Speech Commands: A Public Dataset for Single-Word Speech Recognition","author":"warden","year":"2017"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2762739"},{"key":"ref57","first-page":"1","article-title":"Phone recognition with hierarchical convolutional deep maxout networks","author":"t\u00f3th","year":"2015","journal-title":"EURASIP J Audio Speech Music Process"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683713"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/29.46546"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.213"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2231"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref13","article-title":"Self-Supervised Audio Representation Learning for Mobile Devices","author":"tagliasacchi","year":"0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.2985586"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2938863"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2048"},{"key":"ref17","article-title":"Learning Audio Representations Via Phase Prediction","author":"quitry","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2605"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3084"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054224"},{"key":"ref3","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref6","first-page":"1182","article-title":"Learning robust and multilingual speech representations","author":"kawakami","year":"2020","journal-title":"Proc Findings Assoc Comput Linguistics Empirical Methods Natural Lang Process"},{"key":"ref5","first-page":"12449","author":"baevski","year":"0","journal-title":"wav2vec 2 0 A framework for self-supervised learning of speech representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref49","article-title":"The Kaldi Speech Recognition Toolkit","author":"povey","year":"2011","journal-title":"Proc Automatic Speech Recognition and Understanding"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2702"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref48","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1,” NASA STI\/Recon Tech. Rep.","author":"garofolo","year":"1993"},{"key":"ref47","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Int Conf Learn Representations"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053163"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref44","author":"mikolov","year":"2013","journal-title":"Proc 1st Int Conf Learn Representations"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-2"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09478264.pdf?arnumber=9478264","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T10:53:57Z","timestamp":1652180037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9478264\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3095662","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}