{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:17:37Z","timestamp":1740100657532,"version":"3.37.3"},"reference-count":30,"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"}],"funder":[{"DOI":"10.13039\/501100002875","name":"Chunghwa Telecom Laboratories","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002875","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001868","name":"National Science Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001868","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747569","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6817-6821","source":"Crossref","is-referenced-by-count":7,"title":["Exploring Non-Autoregressive End-to-End Neural Modeling for English Mispronunciation Detection and Diagnosis"],"prefix":"10.1109","author":[{"given":"Hsin-Wei","family":"Wang","sequence":"first","affiliation":[{"name":"National Taiwan Normal University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bi-Cheng","family":"Yan","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsuan-Sheng","family":"Chiu","sequence":"additional","affiliation":[{"name":"Chunghwa Telecom Laboratories,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yung-Chang","family":"Hsu","sequence":"additional","affiliation":[{"name":"EZAI,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Berlin","family":"Chen","sequence":"additional","affiliation":[{"name":"National Taiwan Normal University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref30","first-page":"1049","article-title":"Improving end-to-end modeling for mispronunciation detection with effective augmentation mechanisms","author":"lo","year":"2021","journal-title":"Proceedings of APSIPA ASC"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682654"},{"key":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052975"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1605"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1616"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref16","article-title":"End-to-end continuous speech recognition using attention-based recurrent nn: First results","author":"chorowski","year":"2014","journal-title":"arXiv preprint arXiv 1412 1602"},{"key":"ref17","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proceedings of NIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref28","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"arXiv preprint arXiv 2006 11116"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2621675"},{"key":"ref27","first-page":"27403","article-title":"DARPA TIMIT acoustic-phonetic continuous speech corpus CD-Rom: NIST speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-337"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2623"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2363"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-580"},{"key":"ref7","first-page":"8079","article-title":"A multi-view approach for Mandarin non-native mispronunciation verification","author":"wang","year":"2020","journal-title":"Proceedings of ICASSP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-358"},{"key":"ref9","first-page":"122","article-title":"Pronunciation assessment via a comparison-based system","author":"lee","year":"2013","journal-title":"Proceedings of IEEE SLaTE Workshop"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-566"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proceedings of NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1600"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.154"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1110"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1633"}],"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\/09747569.pdf?arnumber=9747569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:13:59Z","timestamp":1661199239000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747569\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747569","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}