{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:32:49Z","timestamp":1785857569539,"version":"3.56.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682654","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"8132-8136","source":"Crossref","is-referenced-by-count":72,"title":["CNN-RNN-CTC Based End-to-end Mispronunciation Detection and Diagnosis"],"prefix":"10.1109","author":[{"given":"Wai-Kim","family":"Leung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xunying","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Direct acoustics-to-word models for english conversational speech recognition","author":"audhkhasi","year":"2017","journal-title":"arXiv preprint arXiv 1703 06870"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461935"},{"key":"ref12","article-title":"Towards end-to-end speech recognition with deep convolutional neural networks","author":"zhang","year":"2017","journal-title":"arXiv preprint arXiv 1701 00295"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178332"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288864"},{"key":"ref15","first-page":"epfl-conf-210029","article-title":"Analysis of cnn-based speech recognition system using raw speech as input","author":"palaz","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430152"},{"key":"ref17","first-page":"1","article-title":"The needleman-wunsch algorithm for sequence alignment","author":"likic","year":"2008","journal-title":"Lecture given at the 7th Melbourne Bioinformatics Course Bi021 Molecular Science and Biotechnology Institute University of Melbourne"},{"key":"ref18","first-page":"175","article-title":"The htk book","volume":"3","author":"young","year":"2002","journal-title":"Cambridge University Engineering Department"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2010.5684845"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2011.6085985"},{"key":"ref3","article-title":"Automatic derivation of phonological rules for mispronunciation detection in a computer-assisted pronunciation training system","author":"lo","year":"2010","journal-title":"Eleventh Annual Conference of the International Speech Communication Association"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2621675"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2012.6423507"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472856"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.12.008"},{"key":"ref9","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"International Conference on Machine Learning"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682654.pdf?arnumber=8682654","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:14:19Z","timestamp":1657854859000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682654\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682654","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}