{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:44Z","timestamp":1737176864267,"version":"3.33.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832138","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"991-998","source":"Crossref","is-referenced-by-count":0,"title":["Semi-Supervised Learning for Robust Speech Evaluation"],"prefix":"10.1109","author":[{"given":"Huayun","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR) 1 Fusionopolis Way, Connexis #21-01,Singapore,138632"}]},{"given":"Jeremy H.M.","family":"Wong","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR) 1 Fusionopolis Way, Connexis #21-01,Singapore,138632"}]},{"given":"Geyu","family":"Lin","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR) 1 Fusionopolis Way, Connexis #21-01,Singapore,138632"}]},{"given":"Nancy F.","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R),Agency for Science, Technology and Research (A*STAR) 1 Fusionopolis Way, Connexis #21-01,Singapore,138632"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/SLaTE.2015-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596227"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00044-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.5011159"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2953"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2623"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.12.008"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683268"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1766"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383553"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"article-title":"Uncertainty estimation in deep learning with application to spoken language assessment (doctoral thesis)","year":"2019","author":"Malinin","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2238"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078591"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-28"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746743"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979979"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1258"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref20","first-page":"12449","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":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref22","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Ardila"},{"article-title":"Speech recognition and keyword spotting for low-resource languages: Babel project research at cued","volume-title":"Workshop on Spoken Language Technologies for Under-resourced Languages","author":"John","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref29","first-page":"122022","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Technical Report","author":"Radford"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/e19110631"},{"key":"ref32","article-title":"Data augmentation can improve robustness","author":"Rebuffi","year":"2021","journal-title":"NeurIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2016-595"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1259"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1312"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3166"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-139"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832138.pdf?arnumber=10832138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:49:48Z","timestamp":1737100188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832138\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832138","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}