{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:29:16Z","timestamp":1730197756744,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"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":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317374","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:46Z","timestamp":1700507266000},"page":"1955-1959","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Whisper Model for Pronunciation Assessment with Multi-Adapters"],"prefix":"10.1109","author":[{"given":"Jing","family":"Li","sequence":"first","affiliation":[{"name":"Xinjiang University,School of Information Science and Engineering,Urumqi,China"}]},{"given":"Rui","family":"Li","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Information Science and Engineering,Urumqi,China"}]},{"given":"Shen","family":"Guo","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Information Science and Engineering,Urumqi,China"}]},{"given":"Aishan","family":"Wumaier","sequence":"additional","affiliation":[{"name":"Xinjiang University,School of Information Science and Engineering,Urumqi,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/icslp.2002-246"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.5011159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1282"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/slate.2009-13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00044-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2363"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-931"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746743"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979979"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095733"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414451"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-870"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10245"},{"key":"ref14","first-page":"1049","article-title":"Improving end-to-end modeling for mispronunciation detection with effective augmentation mechanisms","volume-title":"Proc. APSIPA ASC 2021","author":"Lo"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404814"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462562"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1087"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/icact56868.2023.10079686"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-industry.29"},{"key":"ref20","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":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Learning multiple visual domains with residual adapters","year":"2017","author":"Rebuffi","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.103"},{"article-title":"What all do audio transformer models hear? probing acoustic representations for language delivery and its structure","year":"2021","author":"Shah","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1259"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1592"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2023,10,31]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317374.pdf?arnumber=10317374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T18:54:50Z","timestamp":1709405690000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317374","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}