________________________________________________________________________This study presents a novel approach to automatic emotion recognition from text. First, emotion generation rules (EGRs) are manually deduced from psychology to represent the conditions for generating emotion. Based on the EGRs, the emotional state of each sentence can be represented as a sequence of semantic labels (SLs) and attributes (ATTs); SLs are defined as the domain-independent features, while ATTs are domain-dependent. The emotion association rules (EARs) represented by SLs and ATTs for each emotion are automatically derived from the sentences in an emotional text corpus using the a priori algorithm. Finally, a separable mixture model (SMM) is adopted to estimate the similarity between an input sentence and the EARs of each emotional state. Since some features defined in this approach are domain-dependent, a dialog system focusing on the students' daily expressions is constructed, and only three emotional states, happy, unhappy, and neutral, are considered for performance evaluation. According to the results of the experiments, given the domain corpus, the proposed approach is promising, and easily ported into other domains.

No abstract

This study presents an approach for automated lip synchronization and smoothing for Chinese visual speech synthesis. A facial animation system with synchronization algorithm is also developed to visualize an existent Text-ToSpeech system. Motion parameters for each viseme are first constructed from video footage of a human speaker. To synchronize the parameter set sequence and speech signal, a maximum direction change algorithm is also proposed to select significant parameter set sequences according to the speech duration. Moreover, to improve the smoothness of coarticulation part under a high speaking rate, four phonemedependent co-articulation functions are generated by integrating the Bernstein-Bézier curve and apparent motion property. A Chinese visual speech synthesis system is built to evaluate the proposed approach. The synthesis result of the proposed system is compared to the real speaker. The coarticulation generated by the proposed approach is also evaluated.

No abstract