{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:16:50Z","timestamp":1784218610527,"version":"3.55.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389685","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["FAT-HuBERT: Front-End Adaptive Training of Hidden-Unit BERT For Distortion-Invariant Robust Speech Recognition"],"prefix":"10.1109","author":[{"given":"Dongning","family":"Yang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanmin","family":"Qian","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,AI Institute Department of Computer Science and Engineering,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3178115"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746314"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref5","article-title":"Representation learning with contrastive predictive coding","author":"den Oord","year":"2018","journal-title":"arXiv preprint arXiv:1807.03748"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","journal-title":"Advances in Neural Information Processing Systems, 2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9053176"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747355"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746929"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-717"},{"key":"ref13","first-page":"6062","article-title":"Improving noise robustness of contrastive speech representation learning with speech reconstruction","author":"HemingWang","year":"2022","journal-title":"IEEE ICASSP"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096308"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-318"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2946789"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045180"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2528171"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1242"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3039600"},{"key":"ref21","article-title":"Multi-variant consistency based self-supervised learning for robust automatic speech recognition","author":"Gao","year":"2021","journal-title":"arXiv preprint arXiv:2112.12522"},{"key":"ref22","article-title":"Joint training of speech enhancement and selfsupervised model for noise-robust asr","author":"Zhu","year":"2022","journal-title":"arXiv preprint arXiv:2205.13293"},{"key":"ref23","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2021.3067147"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref27","article-title":"Deep neural network techniques for monaural speech enhancement: State of the art analysis","author":"Ochieng","year":"2022","journal-title":"arXiv preprint arXiv:2212.00369"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2537"},{"key":"ref29","article-title":"Phaseaware speech enhancement with deep complex u-net","volume-title":"International Conference on Learning Representations","author":"Choi"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref31","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746372"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-659"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003968"},{"key":"ref41","article-title":"A conformer based acoustic model for robust automatic speech recognition","volume-title":"arXiv preprint arXiv:2203.00725","author":"Yang"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389685.pdf?arnumber=10389685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:35:56Z","timestamp":1706027756000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389685\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389685","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}