{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:31Z","timestamp":1775230111351,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100004318","name":"Microsoft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004318","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022474","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"1112-1119","source":"Crossref","is-referenced-by-count":10,"title":["Improving Generalizability of Distilled Self-Supervised Speech Processing Models Under Distorted Settings"],"prefix":"10.1109","author":[{"given":"Kuan-Po","family":"Huang","sequence":"first","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Kuan","family":"Fu","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsu-Yuan","family":"Hsu","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabian Ritter","family":"Gutierrez","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan-Lin","family":"Wang","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang-Hsuan","family":"Tseng","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google Brain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref2","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 Infor-mation Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1775"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747490"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-519"},{"issue":"1","key":"ref7","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"The journal of machine learning research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref9","article-title":"Augmentation adversarial training for self-supervised speaker recognition","author":"Huh","year":"2020","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414291"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1888"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1519"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746220"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747379"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01549"},{"key":"ref18","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746929"},{"key":"ref22","article-title":"Joint training of speech enhancement and self-supervised model for noise-robust asr","author":"Zhu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","article-title":"Mu-san: A music, speech, and noise corpus","author":"Snyder","year":"2015","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref29","article-title":"Data augmenting contrastive learning of speech representations in the time domain","author":"Kharitonov","year":"2020","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref32","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"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022474.pdf?arnumber=10022474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T09:28:50Z","timestamp":1707816530000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022474\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022474","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}