emotion recognition from speech plays an important role in developing affective and intelligent Human Computer Interaction. The goal of this work is to build an automaticemotionvariationdetection(AEVD) system to de...
详细信息
emotion recognition from speech plays an important role in developing affective and intelligent Human Computer Interaction. The goal of this work is to build an automaticemotionvariationdetection(AEVD) system to determine each emotional salient segment in continuous speech. We focus on emotiondetection in angry-neutral speech, which is common in recent studies of AEVD. This work proposes a novel frame-work for AEVD usingmulti-scaledslidingwindow(MSW-AEVD) to assign an emotion class to each window-shift by fusion decisions of all the slidingwindows containing the shift. Firstly, slidingwindow with fixed-length is introduced as the basic procedure, in which several different fusion methods are investigated. Then multi-scaledslidingwindow is employed to support multi-classifiers with different timescale features, in which another two fusion strategies are provided. Finally, a post-processing is applied to refine the final outputs. Performance evaluation is carried out on the public Berlin database EMO-DB. Our experimental results show that proposed MSW-AEVD significantly outperforms the traditional HMM-based AEVD.
暂无评论