{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T19:10:30Z","timestamp":1765825830251,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","funder":[{"DOI":"10.13039\/501100004423","name":"Waseda University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004423","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383590","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"629-635","source":"Crossref","is-referenced-by-count":7,"title":["Analysis of Multimodal Features for Speaking Proficiency Scoring in an Interview Dialogue"],"prefix":"10.1109","author":[{"given":"Mao","family":"Saeki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoichi","family":"Matsuyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Kobashikawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuji","family":"Ogawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsunori","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/15434303.2018.1472265"},{"key":"ref11","first-page":"2440","article-title":"End-to-end memory networks","volume":"2015","author":"sukhbaatar","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683717"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1075\/ijlcr.19001.gab"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15858\/engtea.74.4.201912.153"},{"key":"ref15","first-page":"119","article-title":"The NICT JLE Corpus","volume":"12","author":"izumi","year":"2004","journal-title":"International Journal of the Computer the Internet and Management"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/15434303.2016.1263637"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/19312450709336664"},{"journal-title":"Automated Speaking Assessment Using Language Technologies to Score Spontaneous Speech","year":"2020","author":"zechner","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/SLaTE.2019-23"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3635"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/9781119227793.ch19"},{"key":"ref6","article-title":"Non-verbal signals for turn-taking and feedback","author":"jokinen","year":"2010","journal-title":"Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5913"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-0501"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4441"},{"year":"2018","key":"ref2","article-title":"Common European Framework of Reference For Languages: Learning, Teaching, Assessment"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462562"},{"key":"ref20","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Volume 1 (Long and Short Papers)"},{"key":"ref22","article-title":"OpenFace 2.0: Facial Behavior Analysis Toolkit","author":"baltru\u0161aitis","year":"0","journal-title":"IEEE International Conference on Automatic Face and Gesture Recognition"},{"key":"ref21","article-title":"Cross-dataset learning and person-specific normalisation for automatic Action Unit detection","author":"baltru\u0161aitis","year":"2015","journal-title":"IEEE International Conference on Automatic Face and Gesture Recognition"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383590.pdf?arnumber=9383590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,31]],"date-time":"2021-05-31T21:30:40Z","timestamp":1622496640000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383590\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383590","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}