{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:37:57Z","timestamp":1730230677179,"version":"3.28.0"},"reference-count":19,"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\/icassp43922.2022.9747414","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"6832-6836","source":"Crossref","is-referenced-by-count":3,"title":["Masked Acoustic Unit for Mispronunciation Detection and Correction"],"prefix":"10.1109","author":[{"given":"Zhan","family":"Zhang","sequence":"first","affiliation":[{"name":"Zhejiang University,Department of Information and Electronic Engineering,Zhejiang,China,310007"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuehai","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Department of Information and Electronic Engineering,Zhejiang,China,310007"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianyi","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University,Department of Information and Electronic Engineering,Zhejiang,China,310007"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1693"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424254"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1478"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref14","first-page":"5999","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"5206","article-title":"Librispeech: An asr corpus based on public domain audio books","author":"panayotov","year":"2015","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1110"},{"article-title":"Categorical reparameterization with gumbel-softmax","year":"2016","author":"jang","key":"ref17"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","year":"2020","author":"ren","key":"ref18"},{"article-title":"Parallel wavegan: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","year":"2019","author":"yamamoto","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.04.004"},{"key":"ref3","first-page":"3032","article-title":"An end-to-end mispronunciation detection system for l2 english speech leveraging novel antiphone modeling","author":"yan","year":"2020","journal-title":"Proceedings of the Annual Conference of the International Speech Communication Association INTERSPEECH"},{"key":"ref6","article-title":"First language phonetic drift during second language acquisition","author":"chang","year":"2010","journal-title":"ProQuest LLC"},{"key":"ref5","article-title":"Cnn-rnn-ctc based end-to-end mispronunciation detection and diagnosis","author":"leung","year":"2019","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1350"},{"key":"ref2","first-page":"1","article-title":"End-to-end automatic pronunciation error detection based on improved hybrid ctc\/attention architecture","volume":"20","author":"zhang","year":"2020","journal-title":"Sensors (Switzerland)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00044-8"},{"key":"ref9","first-page":"6533","article-title":"Hubert: How much can a bad teacher benefit asr pretraining?","author":"hsu","year":"2021","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"}],"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\/09747414.pdf?arnumber=9747414","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:06Z","timestamp":1661199066000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747414\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747414","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}