An Approach to Design an Intelligent Parametric Synthesizer for Emotional Speech

摘要

Speech synthesizer is an artificial system to produce speech. But the generation of emotional speech is a difficult task. Though many researchers have been working on this area since a long period, still it is a challenging problem in terms of accuracy. The objective of our work is to design an intelligent model for emotional speech synthesis. An attempt is taken to compute such system using rule based fuzzy model. Initially the required parameters have been considered for the model and are extracted as features. The features are analyzed for each speech segment. At the synthesis level the model has been trained with these parameters properly. Next to it, it has been tested. The tested results show its performance.