{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T17:56:19Z","timestamp":1776880579164,"version":"3.51.2"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746220","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6062-6066","source":"Crossref","is-referenced-by-count":24,"title":["Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction"],"prefix":"10.1109","author":[{"given":"Heming","family":"Wang","sequence":"first","affiliation":[{"name":"The Ohio State University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Qian","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiming","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shujie","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takuya","family":"Yoshioka","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[{"name":"The Ohio State University,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Unsupervised sound separation using mixture invariant training","author":"wisdom","year":"2020","journal-title":"Proceedings of NeurIPS"},{"key":"ref30","article-title":"The rwth\/upb\/forth system combination for the 4th chime challenge evaluation","author":"menne","year":"2016","journal-title":"Computer Speech & Language"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1473"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-2"},{"key":"ref14","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Representation learning with contrastive predictive coding","author":"oord","year":"2018"},{"key":"ref16","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.106"},{"key":"ref18","first-page":"10937","article-title":"Unispeech: Unified speech representation learning with labeled and unlabeled data","author":"wang","year":"2021","journal-title":"Proceedings of ICML"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053569"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003968"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref27","first-page":"187","article-title":"KenLM: Faster and smaller language model queries","author":"heafield","year":"2011","journal-title":"Proceedings of the statistical machine translation"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-220"},{"key":"ref29","first-page":"36","article-title":"The USTC-iFlytek system for CHiME-4 challenge","volume":"4","author":"du","year":"2016","journal-title":"Proc CHiME"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952160"},{"key":"ref8","first-page":"1778","article-title":"The 2020 ESPNet update: New features, broadened applications, performance improvements, and future plans","author":"watanabe","year":"2020","journal-title":"Proceedings of DSLW"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937250"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383500"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2918706"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-717"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"ref24","article-title":"The 4th CHiME speech separation and recognition challenge","author":"vincent","year":"2016"},{"key":"ref23","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746220.pdf?arnumber=9746220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:08:53Z","timestamp":1660594133000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746220","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}