{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:11:00Z","timestamp":1764400260219,"version":"3.46.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249142","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"688-693","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Data Imbalance in Automated Speaking Assessment"],"prefix":"10.1109","author":[{"given":"Fong-Chun","family":"Tsai","sequence":"first","affiliation":[{"name":"National Taiwan Normal University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuan-Tang","family":"Huang","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bi-Cheng","family":"Yan","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tien-Hong","family":"Lo","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Berlin","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","article-title":"Attention-based models for speech recognition","volume-title":"Advances in Neural Information Processing Systems","author":"Chorowski","year":"2015"},{"key":"ref3","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Radford","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.09.002"},{"journal-title":"L2 proficiency assessment using self-supervised speech representations","year":"2022","author":"Bann\u00f2","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.86"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.4324\/9781315165103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/0969594X.2021.1979467"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref10","article-title":"Data2vec: A general framework for selfsupervised learning in speech, vision and language","volume-title":"International conference on machine learning","author":"Baevski","year":"2022"},{"key":"ref11","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","year":"2019","author":"Devlin","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/slt54892.2023.10023019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.011"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0192-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01874"},{"key":"ref19","article-title":"Assessing the prosody of non-native speakers of English: Measures and feature sets","volume-title":"Proceedings of the Tenth International Conference on Language Resources and Evaluation","author":"Coutinho","year":"2016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.09.005"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW58026.2022.00120"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"journal-title":"Common European Framework of Reference for Languages: Learning, Teaching, Assessment","year":"2001","key":"ref23"},{"key":"ref24","article-title":"Visualizing data using t-sne.","author":"Van Der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249142.pdf?arnumber=11249142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:06:13Z","timestamp":1764399973000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249142\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249142","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}