{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T13:51:24Z","timestamp":1769694684899,"version":"3.49.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413953","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7738-7742","source":"Crossref","is-referenced-by-count":14,"title":["Mispronunciation Detection in Non-Native (L2) English with Uncertainty Modeling"],"prefix":"10.1109","author":[{"given":"Daniel","family":"Korzekwa","sequence":"first","affiliation":[{"name":"Amazon Speech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaime","family":"Lorenzo-Trueba","sequence":"additional","affiliation":[{"name":"Amazon Speech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Szymon","family":"Zaporowski","sequence":"additional","affiliation":[{"name":"Gdansk University of Technology, Faculty of ETI,Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shira","family":"Calamaro","sequence":"additional","affiliation":[{"name":"Amazon Speech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Drugman","sequence":"additional","affiliation":[{"name":"Amazon Speech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bozena","family":"Kostek","sequence":"additional","affiliation":[{"name":"Gdansk University of Technology, Faculty of ETI,Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1270"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178993"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2320"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2010.5684845"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref15","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref16","article-title":"Mxnet: A flexible and efficient machine learning library for heterogeneous distributed systems","author":"chen","year":"2015","journal-title":"arXiv preprint arXiv 1512 03385"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2836(70)90057-4"},{"key":"ref18","first-page":"27403","article-title":"Darpa timit acoustic-phonetic continous speech corpus cd-rom. nist speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"STIN"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2621675"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(99)00044-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682654"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2363"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2623"},{"key":"ref7","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TLT.2020.2980261"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/09588220802447651"},{"key":"ref9","article-title":"Implementation of an extended recognition network for mispronunciation detection and diagnosis in computer-assisted pronunciation training","author":"harrison","year":"2009","journal-title":"International Workshop on Speech and Language Technology in Education"},{"key":"ref20","first-page":"5","article-title":"The isle corpus: Italian and german spoken learner’s english","volume":"27","author":"atwell","year":"2003","journal-title":"ICAME Journal Intl Computer Archive of Modern and Medieval English Journal"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/002383098402700405"},{"key":"ref21","article-title":"Constructing a dataset of speech recordings with lombard effect","author":"weber","year":"2020","journal-title":"24th IEEE SPA"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413953.pdf?arnumber=9413953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:38Z","timestamp":1659486038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413953\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413953","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}