{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:57:16Z","timestamp":1776887836678,"version":"3.51.2"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095373","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":19,"title":["Robust Data2VEC: Noise-Robust Speech Representation Learning for ASR by Combining Regression and Improved Contrastive Learning"],"prefix":"10.1109","author":[{"given":"Qiu-Shi","family":"Zhu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}]},{"given":"Long","family":"Zhou","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}]},{"given":"Shu-Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Yu-Chen","family":"Hu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}]},{"given":"Li-Rong","family":"Dai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"tarvainen","year":"2017","journal-title":"Proc of NIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref34","article-title":"Joint training of speech enhancement and self-supervised model for noise-robust asr","author":"zhu","year":"2022","journal-title":"arXiv preprint arXiv 2205 13293"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-022-02075-7"},{"key":"ref31","first-page":"36","article-title":"The ustc-iflytek system for chime-4 challenge","volume":"4","author":"du","year":"2016","journal-title":"Proc CHiME"},{"key":"ref30","first-page":"49","article-title":"The rwth\/upb\/forth system combination for the 4th chime challenge evaluation","author":"menne","year":"2016","journal-title":"Proc of CHiME-4 Workshop"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096615"},{"key":"ref33","article-title":"Data augmentation based consistency contrastive pre-training for automatic speech recognition","author":"gao","year":"2021","journal-title":"arXiv preprint arXiv 2112 12310"},{"key":"ref10","article-title":"Dual-path style learning for end-to-end noise-robust speech recognition","author":"hu","year":"2022","journal-title":"arXiv preprint arXiv 2203 14838"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref1","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Proc of NIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747379"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746220"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746929"},{"key":"ref24","article-title":"Incremental false negative detection for contrastive learning","author":"chen","year":"2022","journal-title":"Proc of ICLR"},{"key":"ref23","article-title":"Are all negatives created equal in contrastive instance discriminationƒ","author":"cai","year":"2020","journal-title":"arXiv preprint arXiv 2010 09084"},{"key":"ref26","first-page":"49","article-title":"The rwth\/upb\/forth system combination for the 4th chime challenge evaluation","author":"menne","year":"2016","journal-title":"Proc of CHiME-4 Workshop"},{"key":"ref25","first-page":"27356","article-title":"Robust contrastive learning using negative samples with diminished semantics","volume":"34","author":"ge","year":"2021","journal-title":"Proc of NIPS"},{"key":"ref20","first-page":"21798","article-title":"Hard negative mixing for contrastive learning","volume":"33","author":"kalantidis","year":"2020","journal-title":"Proc of NIPS"},{"key":"ref22","article-title":"Contrastive learning with hard negative samples","author":"robinson","year":"2021","journal-title":"Proc of ICLR"},{"key":"ref21","first-page":"8765","article-title":"Debiased contrastive learning","volume":"33","author":"chuang","year":"2020","journal-title":"Proc of NIPS"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref27","article-title":"Musan: A music, speech, and noise corpus","author":"snyder","year":"2015","journal-title":"arXiv preprint arXiv 1510 08484"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746314"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-67"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747755"},{"key":"ref4","article-title":"Speecht5: Unified-modal encoder-decoder pre-training for spoken language processing","author":"ao","year":"2021","journal-title":"arXiv preprint arXiv 2110 07058"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","article-title":"Speechlm: Enhanced speech pre-training with unpaired textual data","author":"zhang","year":"2022","journal-title":"arXiv preprint arXiv 2209 15329"},{"key":"ref5","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume":"162","author":"baevski","year":"2022","journal-title":"ICML"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095373.pdf?arnumber=10095373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:57:05Z","timestamp":1700506625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095373","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}