{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:39:15Z","timestamp":1767339555274},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747774","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6807-6811","source":"Crossref","is-referenced-by-count":3,"title":["A Universal Ordinal Regression for Assessing Phoneme-Level Pronunciation"],"prefix":"10.1109","author":[{"given":"Shaoguang","family":"Mao","sequence":"first","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Frank","family":"Soong","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Yan","family":"Xia","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]},{"given":"Jonathan","family":"Tien","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Automatic pronunciation error detection: an acoustic-phonetic approach","author":"truong","year":"2004","journal-title":"InSTIL\/ICALL Symposium 2004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-597"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2526782"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2621675"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/SLaTE.2009-12","article-title":"Implementation of an extended recognition network for mispronunciation detection and diagnosis in computer-assisted pronunciation training","author":"harrison","year":"2009","journal-title":"Slate"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-280"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461841"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052975"},{"key":"ref18","article-title":"A Full Text-Dependent End to End Mispronunciation Detection and Diagnosis with Easy Data Augmentation Techniques","author":"fu","year":"2021","journal-title":"arXiv preprint arXiv 2104 08428"},{"key":"ref19","article-title":"Maximum f1-score training for end-to-end mispronunciation detection and diagnosis of L2 English speech","author":"yan","year":"2021","journal-title":"arXiv preprint arXiv 2108 13035"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462635"},{"key":"ref3","article-title":"Automatic pronunciation error detection and guidance for foreign language learning","author":"jo","year":"1998","journal-title":"Intl Conference on Spoken Language Processing"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.08.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-566"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2953"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.12.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.596227"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413659"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607890"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413953"},{"key":"ref22","first-page":"4920","article-title":"Ordinal regression with multiple output CNN for age estimation","author":"niu","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682187"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1259"},{"key":"ref23","first-page":"5206","article-title":"Librispeech: an asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"ICASSP"},{"key":"ref25","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747774.pdf?arnumber=9747774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:21:00Z","timestamp":1727061660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747774\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747774","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}