Malay speech recognition to determine emotion using fuzzy logic / Siti Nazirah Abd Rahim

Emotion classification is something interesting, but to develop a system that can classify the type of emotion in speech is a difficult process. This is because it becomes complicated when people try to determine what type of emotions without seeing the facial expression. This project focuses on developing the prototype that can classify the type of emotion just by listening to the voice recorded only. The significant of this project is it can use in many industries such as operator service, counselor and lawyer. The objective of this project is to determine the type of emotion in recorded speech and to develop a system that can classify what type of emotion using fuzzy logic technique. To ensure the ability of this project, the testing process will be conducted using 50 samples of recorded speech. This project only covers three types of emotion that are happy, sad and angry. The classifying process is using average frequency of each recorded speech. This project also limited to Malay language and female voice only. As a conclusion, the prototype is able to determine the type of emotion in recorded speech using fuzzy logic technique.