Lv, L., Jiang, D., Wang, F., Sahli, H., & Verhelst, W. (2012). Audio Visual Emotion Recognition Based on the Triple Stream DBN Models. Computer Engineering, 38, 161-166.

@article{770345340a0141f3b1a5826865c141e9,
title = "Audio Visual Emotion Recognition Based on the Triple Stream DBN Models",
abstract = "This paper presents a triple stream Dynamic Bayesian Networks(DNB) mode (T_AsyDBN) for audio visual emotion recognition, in which the two audio stream are synchronous at the state level, which they are asynchronous with the visual stream within controllable constraints. MFCC features and local prosodic features are extracted as audio features, while dimensional geometric features as well facial action units' coefficients are extracted as visual features. Emotion recognition experiment show that by adjusting the asynchrony constraint, T_AsDBN performs better than the two stream audio visual DBN model(Asy_DBN), with average recognition rate improves from 52.14% to 63.71%.",
keywords = "Dynamic Bayesian Networks(DBN), audio visual fusion, emotion recognition, asynchrony constraint, weight",
author = "Lanlan Lv and Dongmei Jiang and Fengna Wang and Hichem Sahli and Werner Verhelst",
year = "2012",
month = mar,
day = "5",
language = "English",
volume = "38",
pages = "161--166",
journal = "Computer Engineering",
issn = "1000-3428",
publisher = "Shanghai Jisuanji Xuehui/Shanghai Computer Society",
}