{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T07:04:39Z","timestamp":1760598279586,"version":"3.37.3"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447220","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12396-12400","source":"Crossref","is-referenced-by-count":1,"title":["Boosting Speech Enhancement with Clean Self-Supervised Features Via Conditional Variational Autoencoders"],"prefix":"10.1109","author":[{"given":"Yoonhyung","family":"Lee","sequence":"first","affiliation":[{"name":"Seoul National University,Dept. of Electrical and Computer Engineering,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyomin","family":"Jung","sequence":"additional","affiliation":[{"name":"Seoul National University,Dept. of Electrical and Computer Engineering,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10727"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095118"},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-582"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-695"},{"key":"ref9","first-page":"9361","article-title":"Squeezeformer: An efficient transformer for automatic speech recognition","volume":"35","author":"Kim et al","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2207"},{"key":"ref12","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume":"34","author":"Choi","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref14","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-toend text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref15","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","author":"Kingma","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Neural spline flows","volume":"32","author":"Durkan","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"19667","article-title":"Nvae: A deep hierarchical variational autoencoder","volume":"33","author":"Vahdat","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Ladder variational autoencoders","volume":"29","author":"S\u00f8nderby","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1021"},{"article-title":"Noisy speech database for training speech enhancement algorithms and tts models, 2016 [sound]","year":"2017","author":"Valentini-Botinhao","key":"ref20"},{"article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"International Conference on Learning Representations","author":"Lee","key":"ref21"},{"key":"ref22","first-page":"27826","article-title":"Unsupervised speech recognition","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Baevski","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-225"},{"article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097255"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447220.pdf?arnumber=10447220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:32:42Z","timestamp":1722576762000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447220","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}