{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:14:31Z","timestamp":1780676071994,"version":"3.54.1"},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383575","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"344-350","source":"Crossref","is-referenced-by-count":118,"title":["Audio Albert: A Lite Bert for Self-Supervised Learning of Audio Representation"],"prefix":"10.1109","author":[{"given":"Po-Han","family":"Chi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei-Hung","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsung-Han","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun-Cheng","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yen-Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shang-Wen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Albert: A lite bert for self-supervised learning of language representations","author":"lan","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref11","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref13","first-page":"5753","article-title":"Xlnet: Generalized autoregressive pre-training for language understanding","author":"yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Roberta: A robustly optimized bert pre-training approach","author":"liu","year":"2019"},{"key":"ref15","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref17","article-title":"Speech-XLNet: Unsupervised Acoustic Model Pre-training For Self-Attention Networks","author":"song","year":"2019"},{"key":"ref18","article-title":"vqwav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019","journal-title":"International Conference on Learning Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2025"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017","journal-title":"Proc Interspeech 2017"},{"key":"ref4","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref3","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref6","article-title":"Improving transformer-based speech recognition using unsupervised pre-training","author":"jiang","year":"2019"},{"key":"ref29","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3167"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref1","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/735"},{"key":"ref22","article-title":"Universal transformers","author":"dehghani","year":"2019","journal-title":"US Patent App 16\/417 587"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016292"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054675"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1356"},{"key":"ref26","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2599"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","location":"Shenzhen, China","start":{"date-parts":[[2021,1,19]]},"end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383575.pdf?arnumber=9383575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T21:30:55Z","timestamp":1622496655000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383575\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383575","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}