Adding an Emotions Filter to Malay Text-to-Speech System

In this paper we present the findings of our research which aims to develop an emotions filter that can be added to an existing Malay text-to-speech system to produce an output expressing happiness, anger, sadness and fear. The end goal is to produce an output that is as natural as possible, thus contributing towards the enhancement of the existing system. The emotions filter was developed by manipulating pitch and duration of the output using a rule-based approach. The data was made up of emotional sentences produced by a female native speaker of Malay. The information extracted from the analysis was used to develop the filter. The emotional speech output underwent several acceptance tests. The results showed that the emotions filter developed was compatible with FASIH and other TTS systems using the rule-based approach of prosodic manipulation. However, further work need to be done to enhance the naturalness of the output.