Human Emotion Recognition by Audio Signals using MLP Classifier

Abstract

The capacity to identify emotions from speech has drawn increasing attention throughout time. Speech emotion recognition is an emerging topic in the domain of human computer interaction It can be used for a wide range of things, such as communicating with robots, banking, contact centres, car dashboards, video games, and more. The process of accurately determining a human’s emotion from their speech is called speech emotion recognition. It enhances computer and human communication. Despite the challenge of annotating audio and the subjective nature of emotions, SER makes it possible to forecast a person’s emotional state. The benchmark RAVDESS dataset is used in this study’s analysis of speech emotion. We attempted to locate underlying emotions in speech by examining the acoustic properties of recorded audio data.