Speech Emotion Recognition Using Mel-Frequency Cepstral Coefficients

Speech Emotion Recognition (SER) has multiple applications in computational psychology, as well as human- computer interaction, and it also plays a major role in these fields. The accuracy of any machine learning technique is greatly impacted by the extraction as well as the appearance of features. Mel Frequency Cepstrum Coefficient (MFCC) is a frequently used framework across many domains to simulate the characteristics of a signal that contains sound. This study is all about using Mel Frequency Cepstral Coefficients, or MFCCs for short. These are popular tools this use when figuring out emotions in speech signals.The goal here is to see how well MFCCs work in picking up sounds that show different feelings. By using machine learning techniques, like support vector machines (SVM) or even neural networks, this can classify emotions with the MFCC features this have gathered. In this paper, this will look at what others have done in the field of speech emotion recognition. This will also suggest ways to set up systems that detect emotions based on MFCCs. It gives us helpful insights into how Mel frequency features can really help us understand emotions expressed in speech.