{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T07:23:42Z","timestamp":1730273022198,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1109\/iscslp.2016.7918453","type":"proceedings-article","created":{"date-parts":[[2017,5,12]],"date-time":"2017-05-12T22:22:40Z","timestamp":1494627760000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["A multi-channel\/multi-speaker interactive 3D audio-visual speech corpus in Mandarin"],"prefix":"10.1109","author":[{"given":"Jun","family":"Yu","sequence":"first","affiliation":[]},{"given":"Rongfeng","family":"Su","sequence":"additional","affiliation":[]},{"given":"Lan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Wenpeng","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"342","volume":"4","author":"xu","year":"2004","journal-title":"Depth vs intensity Which is more important for face recognition?"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2006.12.018"},{"key":"ref12","first-page":"125","author":"sui","year":"2012","journal-title":"A 3D Audio-Visual Corpus for Speech Recognition"},{"key":"ref13","first-page":"299","author":"zhang","year":"2014","journal-title":"A multi-channel\/multi-speaker articulatory corpus in Mandarin for speech visualization"},{"key":"ref14","first-page":"602","author":"wang","year":"2014","journal-title":"Multi-level adaptive network for accented Mandarin speech recognition"},{"year":"0","key":"ref15"},{"key":"ref16","first-page":"321","volume":"3","author":"haigh","year":"1993","journal-title":"Robust voice activity detection using cepstral features"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.protcy.2012.10.029"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/34.982900"},{"key":"ref3","first-page":"2017","author":"patterson","year":"2002","journal-title":"CUAVE A new audio-visual corpus for multimodal human-computer interface research"},{"journal-title":"Biometric Person Recognition Face Speech and Fusion","year":"2008","author":"sanderson","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref7","first-page":"235","author":"hazen","year":"2004","journal-title":"A segment-based audio-visual speech recognizer Data collection development and initial experiments"},{"key":"ref2","first-page":"851","volume":"7","author":"movellan","year":"1995","journal-title":"Visual Speech Recognition with Stochastic Networks"},{"journal-title":"Automatic lipreading to enhance speech recognition (speech reading)","year":"1984","author":"petajan","key":"ref1"},{"key":"ref9","first-page":"22","author":"matthews","year":"2001","journal-title":"A comparison of model and transform-based visual features for audio-visual LVCSR"}],"event":{"name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2016,10,17]]},"location":"Tianjin, China","end":{"date-parts":[[2016,10,20]]}},"container-title":["2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7912121\/7918361\/07918453.pdf?arnumber=7918453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,5,22]],"date-time":"2017-05-22T17:45:43Z","timestamp":1495475143000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7918453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/iscslp.2016.7918453","relation":{},"subject":[],"published":{"date-parts":[[2016,10]]}}}