TY - JOUR
T1 - Relevance units machine based dimensional and continuous speech emotion prediction
AU - Wang, Fengna
AU - Sahli, Hichem
AU - Gao, Junbin
AU - Jiang, Dongmei
AU - Verhelst, Werner
N1 - Includes bibliographical references
PY - 2015/11
Y1 - 2015/11
N2 - Emotion plays a significant role in human-computer interaction. The continuing improvements in speech technology have led to many new and fascinating applications in human-computer interaction, context aware computing and computer mediated communication. Such applications require reliable online recognition of the user’s affect. However most emotion recognition systems are based on speech via an isolated short sentence or word. We present a framework for online emotion recognition from speech. On the front-end, a voice activity detection algorithm is used to segment the input speech, and features are estimated to model long-term properties. Then, dimensional and continuous emotion recognition is performed via a Relevance Units Machine (RUM). The advantages of the proposed system are: (i) its computational efficiency in run-time (regression outputs can be produced continuously in pseudo real-time), (ii) RUM offers superior sparsity to the well-known Support Vector Regression (SVR) and Relevance Vector Machine for regression (RVR), and (iii) RUM’s predictive performance is comparable to SVR and RVR.
AB - Emotion plays a significant role in human-computer interaction. The continuing improvements in speech technology have led to many new and fascinating applications in human-computer interaction, context aware computing and computer mediated communication. Such applications require reliable online recognition of the user’s affect. However most emotion recognition systems are based on speech via an isolated short sentence or word. We present a framework for online emotion recognition from speech. On the front-end, a voice activity detection algorithm is used to segment the input speech, and features are estimated to model long-term properties. Then, dimensional and continuous emotion recognition is performed via a Relevance Units Machine (RUM). The advantages of the proposed system are: (i) its computational efficiency in run-time (regression outputs can be produced continuously in pseudo real-time), (ii) RUM offers superior sparsity to the well-known Support Vector Regression (SVR) and Relevance Vector Machine for regression (RVR), and (iii) RUM’s predictive performance is comparable to SVR and RVR.
KW - Relevance units machineq
KW - Continuous speech emotion regression
KW - Dimensional emotion modeling
U2 - 10.1007/s11042-014-2319-1
DO - 10.1007/s11042-014-2319-1
M3 - Article
SN - 1380-7501
VL - 74
SP - 9983
EP - 1000
JO - Multimedia Tools and Applications
JF - Multimedia Tools and Applications
ER -