{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:06:35Z","timestamp":1760609195506,"version":"3.28.0"},"reference-count":55,"publisher":"IEEE","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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1109\/ijcnn.2019.8852153","type":"proceedings-article","created":{"date-parts":[[2019,9,30]],"date-time":"2019-09-30T23:44:32Z","timestamp":1569887072000},"page":"1-8","source":"Crossref","is-referenced-by-count":10,"title":["Autoencoder-Based Articulatory-to-Acoustic Mapping for Ultrasound Silent Speech Interfaces"],"prefix":"10.1109","author":[{"given":"Gabor","family":"Gosztolya","sequence":"first","affiliation":[]},{"given":"Adam","family":"Pinter","sequence":"additional","affiliation":[]},{"given":"Laszlo","family":"Toth","sequence":"additional","affiliation":[]},{"given":"Tamas","family":"Grosz","sequence":"additional","affiliation":[]},{"given":"Alexandra","family":"Marko","sequence":"additional","affiliation":[]},{"given":"Tamas Gabor","family":"Csapo","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"2157","article-title":"Error analysis of extracted´ tongue contours from 2D ultrasound images","author":"abor csap\u00b4 o","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1080\/02699200500113558"},{"key":"ref33","first-page":"20","article-title":"Deep Neural Network Language Models","author":"arisoy","year":"2012","journal-title":"Proceedings of the NAACL-HLT 2012 Workshop Will We Ever Really Replace the N-gram Modelƒ On the Future of Language Modeling for HLT"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2752365"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/S0095-4470(19)30822-8","article-title":"Analysis of real-time ultrasound images of tongue configuration using a griddigitizing system","volume":"11","author":"stone","year":"1983","journal-title":"Journal of Phonetics"},{"key":"ref36","first-page":"2672","article-title":"Generative Adversarial Nets","author":"goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems 27 (NIPS 2014)"},{"key":"ref35","article-title":"Prediction of F0 based on articulatory features using DNN","author":"zhao","year":"2017","journal-title":"Proc ISSPIT"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-715"},{"key":"ref28","first-page":"1169","article-title":"Enhancing multimodal silent speech interfaces with feature selection","author":"freitas","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1565"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472852"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326078"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.002"},{"key":"ref20","first-page":"573","article-title":"Estimation of fundamental frequency from surface electromyographic data: EMG-to-F0","author":"nakamura","year":"2011","journal-title":"Proc ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280404"},{"key":"ref21","first-page":"1164","article-title":"Towards a practical silent speech recognition system","author":"deng","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2740000"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2738568"},{"key":"ref26","first-page":"3167","author":"wand","year":"2018","journal-title":"Domain-Adversarial Training for Session Independent EMG-based Speech Recognition"},{"key":"ref25","article-title":"Session-Independent Array-Based EMG-to-Speech Conversion using Convolutional Neural Networks","author":"diener","year":"2018","journal-title":"13th ITG conference on Speech Communication"},{"journal-title":"Mel log spectrum approximation (MLSA) filter for speech synthesis","year":"0","author":"imai","key":"ref50"},{"key":"ref51","article-title":"Information Content of Projections and Reconstruction of Objects in Discrete Tomography","author":"varga","year":"2013","journal-title":"Ph D thesis"},{"year":"2001","key":"ref55","article-title":"ITU-R recommendation BS.1534: Method for the subjective assessment of intermediate audio quality"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref53","article-title":"Searching for activation functions","author":"ramachandran","year":"2018","journal-title":"Proceedings of ICL"},{"article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","year":"2015","author":"abadi","key":"ref52"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.4984122"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952701"},{"key":"ref40","first-page":"318","article-title":"Learning internal representations by error propagation","author":"rumelhart","year":"1986","journal-title":"Parallel Distributed Processing Explorations in the Microstructure of Cognition Volume 1 Foundations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289039"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-1906"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005119"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2758999"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2484"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.medengphy.2007.05.003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2757263"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.11.004"},{"key":"ref3","first-page":"89","article-title":"Towards a Practical Silent Speech Interface Based on Vocal Tract Imaging","author":"denby","year":"2011","journal-title":"Proc 9th Int Seminar on Speech Production (ISSP) 2011"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-385"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"593","DOI":"10.21437\/Interspeech.2011-239","article-title":"Statistical Mapping Between Articulatory and Acoustic Data for an Ultrasound-Based Silent Speech Interface","author":"hueber","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461732"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-939"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.21437\/ICSLP.1994-275","article-title":"Mel-generalized cepstral analysis – a unified approach to speech spectral estimation","author":"tokuda","year":"1994","journal-title":"Proceedings of ICSLP"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1078"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46681-1_50"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.296"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1121\/1.2951592"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref42","first-page":"365","article-title":"Scheduled denoising autoencoders","author":"geras","year":"2015","journal-title":"Proceedings of ICL"},{"key":"ref41","first-page":"1","article-title":"Learning transformations of musical material using Gated Autoencoders","author":"lattner","year":"2017","journal-title":"Proc CSM"},{"key":"ref44","first-page":"4091","article-title":"Learning hierarchical features from generative models","author":"zhao","year":"2017","journal-title":"Proceedings of ICML"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/PCS.2018.8456308"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2019,7,14]]},"location":"Budapest, Hungary","end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8840768\/8851681\/08852153.pdf?arnumber=8852153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T12:26:23Z","timestamp":1664540783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8852153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8852153","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}