Toward a Rule-Based Synthesis of Emotional Speech on Linguistic Descriptions of Perception

Abstract

Abstract. This paper reports rules for morphing a voice to make it be perceived as containing various primitive features, for example, to make it sound more "bright" or "dark". In a previous work we proposed a three-layered model, which contains emotional speech, primitive features, and acoustic features, for the perception of emotional speech. By experiments and acoustic analysis, we built the relationships between the three layers and reported that such relationships are significant. Then, a bottom-up method was adopted in order to verify the relationships. That is, we morphed (resynthesized) a speech voice by composing acoustic features in the bottommost layer to produce a voice in which listeners could perceive a single or multiple primitive features, which could be further perceived as different categories of emotion. The intermediate results show that the relationships of the model built in previous work are valid.

A three-layered model for expressive speech perception

“…We use the semantic primitive specifications with corresponding acoustic features of the first step to resynthesize the expressive speech utterances, and ask human subjects to evaluate the effectiveness of the resynthesized utterances. This approach includes three techniques: (1) a voice-morphed technique for rule verification, (2) expression of the relationships built by step 1 as rules, and (3) examination of various types of human perception of emotion as well as the intensity of the perceptions (Huang and Akagi, 2005).…”