Automatic Hierarchical Classification of Emotional Speech

Zhongzhe Xiao (1) , Emmanuel Dellandréa (1) , Weibei Dou (2) , Liming Chen (1)

1 imagine - Extraction de Caractéristiques et Identification
2 TNLIST - Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing.

Speech emotion is high semantic information and its automatic analysis may have many applications such as smart human-computer interactions or multimedia indexing. As a pattern recognition problem, the feature selection and the structure of the classifier are two important aspects for automatic speech emotion classification. In this paper, we propose a novel feature selection scheme based on the evidence theory. Furthermore, we also present a new automatic approach for constructing a hierarchical classifier, which allows better performance than a global classifier as it is mostly used in the literature. Experimented on the Berlin database, our approach showed its effectiveness, scoring a recognition rate up to 78.64%.

Domaines: Informatique [cs]

Zhongzhe Xiao, Emmanuel Dellandréa, Weibei Dou, Liming Chen. Automatic Hierarchical Classification of Emotional Speech. 9th International Symposium on Multimedia Workshops, ISMW 2007, Dec 2007, Taichung, Taiwan, Taiwan. pp.291-296, ⟨10.1109/ISM.Workshops.2007.56⟩. ⟨hal-01589817⟩