{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:03:22Z","timestamp":1775199802966,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434658","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Lightweight Wasserstein Audio-Visual Model for Unified Speech Enhancement and Separation"],"prefix":"10.1109","author":[{"given":"Jisoo","family":"Park","sequence":"first","affiliation":[{"name":"Chung-Ang University,Department of Artificial Intelligence,South Korea"}]},{"given":"Seonghak","family":"Lee","sequence":"additional","affiliation":[{"name":"Chung-Ang University,Department of Computer Science and Engineering,South Korea"}]},{"given":"Guisik","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Electronics Technology Institute,South Korea"}]},{"given":"Taewoo","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Electronics Technology Institute,South Korea"}]},{"given":"Junseok","family":"Kwon","sequence":"additional","affiliation":[{"name":"Chung-Ang University,Department of Artificial Intelligence,South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389724"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"ref7","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3000593"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2018.8516711"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414060"},{"key":"ref11","article-title":"Wasserstein auto-encoders","author":"Tolstikhin","year":"2018","journal-title":"ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-3114"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref15","article-title":"Audio-visual speech processing using deep learning techniques","author":"Ideli","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2671"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP45357.2019.8969244"},{"key":"ref18","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053164"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-1441"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-517"},{"key":"ref22","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"NIPS","author":"Kong","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445985"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref28","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022","journal-title":"Interspeech"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2098"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/AVSEC.2024-8"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1990.10474930"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref33","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"The Journal of Machine Learning Research"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref36","article-title":"Clearervoice-studio","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434658.pdf?arnumber=11434658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:57:52Z","timestamp":1775192272000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434658\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434658","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}