As technology has developed so has our methods of interacting with them. Voice Interaction has become a major field in Human Computer Interaction. Today, we can successfully use our voice to give commands to different software. This is achieved using Natural Language Processing (NLP), i.e., the linguistic aspect. In this paper, we try to understand if the acoustic approach can be used for emotion recognition. Here, we use the sound waves from human voices to analyze the underlying tone of the speaker and classify it according to their emotion. This paper compares between different features extraction techniques of the audio and compares how different feature extraction techniques perform individually and together on audio data.