Speech recognition to determine emotions using quick propagation neural network / Aisyah Mohamad Tojid

Emotions play important roles in expressing feelings as it tend to make people acts differently. Determine emotions of other people are less complicated if we are facing
each other rather than from voice independently such as conversation in telephone. A main industry that major dealing with telephone as a medium for services is call center. Thus it is a significant step to developing a prototype system for this industry. This project is focusing on speech recognition to determine emotions in call center
environment. The objectives of this project are to identify the quick propagation neural network, determine the emotion through the recorded speech and develop the prototype system. This system will implement the quick propagation neural network using 65 of speech signal as a sample data. Two features will be extracted from each speech signal which are the Fundamental Track Frequency (FTT) and Mel Frequency Ceptral Coefficient (MFCC). It covers types of emotions which are happy, sad and anger
emotions state. However to ensure the ability of the prototype, few experiments are being conducted to achieved the satisfy values for parameter for the prototype inputs to achieve the efficiency. In a conclusion, the prototype is able to determine emotions states from
voice using Quick Propagation neural network.