{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:31Z","timestamp":1740132871726,"version":"3.37.3"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1736123","61572450","61303150"],"award-info":[{"award-number":["U1736123","61572450","61303150"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Anhui Provincial Natural Science Foundation","doi-asserted-by":"crossref","award":["1708085QF138"],"award-info":[{"award-number":["1708085QF138"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["WK2350000002"],"award-info":[{"award-number":["WK2350000002"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/tmm.2018.2887027","type":"journal-article","created":{"date-parts":[[2018,12,18]],"date-time":"2018-12-18T00:37:32Z","timestamp":1545093452000},"page":"1621-1632","source":"Crossref","is-referenced-by-count":11,"title":["BLTRCNN-Based 3-D Articulatory Movement Prediction: Learning Articulatory Synchronicity From Both Text and Audio Inputs"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6403-761X","authenticated-orcid":false,"given":"Lingyun","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3197-8103","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5688-4130","authenticated-orcid":false,"given":"Qiang","family":"Ling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-33"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref33","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"0","journal-title":"NIPS Deep Learning Workshop"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref31","first-page":"115","article-title":"Learning precise timing with LSTM recurrent networks","volume":"3","author":"gers","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.04.028"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref36","first-page":"550","article-title":"Residual networks behave like ensembles of relatively shallow networks","author":"veit","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00790"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709888"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAE.2017.8291424"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2279659"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref21","article-title":"Convolutional networks for images, speech, and time series","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","author":"bishop","year":"1995","journal-title":"Neural Networks for Pattern Recognition"},{"key":"ref23","first-page":"237","article-title":"Improved bottleneck features using pretrained deep neural networks","author":"yu","year":"0","journal-title":"Proc 12th Annu Conf Int Speech Commun Assoc"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1109\/TCYB.2014.2341737","article-title":"A video, text, and speech-driven realistic 3-D virtual head for human–machine interface","volume":"45","author":"yu","year":"2015","journal-title":"IEEE Trans Cybern"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1998.698623"},{"article-title":"Articulatory information for robust speech recognition","year":"2010","author":"mitra","key":"ref11"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178812"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.001"},{"key":"ref14","first-page":"866","article-title":"Deep architectures for articulatory inversion","author":"uria","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref15","article-title":"A deep neural network for acoustic-articulatory speech inversion","author":"uria","year":"0","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref16","first-page":"2192","article-title":"Articulatory movement prediction using deep bidirectional long short-term memory based recurrent neural networks and word\/phone embeddings","author":"zhu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820703"},{"key":"ref18","first-page":"1505","article-title":"Announcing the electromagnetic articulography (day 1) subset of the mngu0 articulatory corpus","author":"richmond","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.06.006"},{"key":"ref4","first-page":"1174","article-title":"Opti-speech: A real-time, 3-D visual feedback system for speech training","author":"katz","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2030637"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.888009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052239"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0093-934X(87)90058-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2014796"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.intcom.2009.12.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0730-725X(87)90477-2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-4578-0"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"920","DOI":"10.1109\/TCSVT.2016.2643504","article-title":"Real-Time 3d facial animation: From appearance to internal articulators","volume":"28","author":"yu","year":"2018","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref48","first-page":"2835","article-title":"Preliminary inversion mapping results with a new EMA corpus","author":"richmond","year":"0","journal-title":"Proc 10th Annu Conf Int Speech Commun Assoc"},{"key":"ref47","first-page":"923","article-title":"Speech-driven articulator motion synthesis with deep neural networks","volume":"6","author":"tang","year":"2016","journal-title":"ACTA Automatica Sinica"},{"key":"ref42","first-page":"1","article-title":"Pearson correlation coefficient","author":"benesty","year":"2009","journal-title":"Noise Reduction in Speech Processing"},{"key":"ref41","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"0","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref44","first-page":"834","article-title":"HMM-based text-to-articulatory-movement prediction and analysis of critical articulators","author":"ling","year":"0","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"article-title":"Word2vec Explained: Deriving Mikolov et al.'s negative-sampling word-embedding method","year":"2014","author":"goldberg","key":"ref43"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8743377\/08579230.pdf?arnumber=8579230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T11:58:58Z","timestamp":1720871938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8579230\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":49,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2887027","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2019,7]]}}}