{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:18:13Z","timestamp":1776885493692,"version":"3.51.2"},"reference-count":24,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icasspw62465.2024.10625802","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"645-649","source":"Crossref","is-referenced-by-count":2,"title":["Integrating Self-Supervised Speech Model with Pseudo Word-Level Targets from Visually-Grounded Speech Model"],"prefix":"10.1109","author":[{"given":"Hung-Chieh","family":"Fang","sequence":"first","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nai-Xuan","family":"Ye","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Jen","family":"Shih","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Puyuan","family":"Peng","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsuan-Fu","family":"Wang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Layne","family":"Berry","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Harwath","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12967"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1227"},{"key":"ref4","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"International Conference on Learning Representations (ICLR)","author":"Shi"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.411"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682666"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2044"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10652"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023079"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-96"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747103"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022954"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096882"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-135"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1718"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746137"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.496"},{"key":"ref22","article-title":"Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces","volume":"abs\/1805.10190","author":"Coucke","year":"2018","journal-title":"ArXiv"},{"key":"ref23","article-title":"The zero resource speech benchmark 2021: Metrics and baselines for unsupervised spoken language modeling","volume":"abs\/2011.11588","author":"Nguyen","year":"2020","journal-title":"ArXiv"},{"key":"ref24","article-title":"Are word boundaries useful for unsupervised language learning?","volume":"abs\/2210.02956","author":"Nguyen","year":"2022","journal-title":"ArXiv"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10625802.pdf?arnumber=10625802","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T05:46:41Z","timestamp":1723787201000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10625802\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10625802","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}