{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:42:58Z","timestamp":1730230978157,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095156","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Raw Ultrasound-Based Phonetic Segments Classification Via Mask Modeling"],"prefix":"10.1109","author":[{"given":"Kang","family":"You","sequence":"first","affiliation":[{"name":"Tongji University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kele","family":"Xu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunsheng","family":"Xiong","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qisheng","family":"Xu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Feng","sequence":"additional","affiliation":[{"name":"Tongji University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tam\u00e1s G\u00e1bor","family":"Csap\u00f3","sequence":"additional","affiliation":[{"name":"Budapest University of Technology and Economics,Budapest,Hungary"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.4984122"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952701"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350596"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.02.002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1080\/02699200500113558"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3109\/02699206.2012.759626"},{"key":"ref17","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv 2010 11419"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref18","article-title":"Ultrasuite: A repository of ultrasound and acoustic data from child speech therapy sessions","volume":"abs 1907 835","author":"eshky","year":"2019","journal-title":"CoRR"},{"key":"ref8","article-title":"Eigentongue feature extraction for an ultrasound-based silent speech interface","volume":"1","author":"hueber","year":"2007","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref7","article-title":"Revealing the dark secrets of masked image modeling","author":"xie","year":"2022","journal-title":"arXiv preprint arXiv 2205 13543"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-410"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.5036466"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.002"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746804"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683564"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095156.pdf?arnumber=10095156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:58:38Z","timestamp":1699901918000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095156","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}