In the field of HCI, one of the most common researched topics is speech emotion recognition. Many researchers are working on systems to classify different emotions from human expression. This is done in order to make HCI and human interfaces more efficient and productive, as well as to build systems that behave intelligently like humans. We conducted an experiment to see if we could recognise emotions from human expression. Neutral, rage, excitement, and sorrow were among the emotions shown for

more »

... the experiments. Necessary work has been done on this topic and carefully examination is also being done. We have researched on multiple algorithms which include CNN, SVM, FFT, and MFCC. We examined the fundamentals of a speech emotion recognition system and explored various pre-processing, feature extraction, and classification techniques for the system in this paper. Elicited, Prosodic, and Spectral features are the three types of features. The classifications were carried out for a variety of classifiers. Hidden Markov Model (HMM), Gaussian Mixtures Model (GMM), Support Vector Machine (SVM). Artificial Neural Network (ANN), and K-nearest neighbour (KNN) are some of the techniques used to distinguish various emotions from human expression. Dataset collection is one of the most important tasks. A lot of work has been done on collecting datasets on emotion recognition. In this research, we researched on various datasets like interactive emotional motion capture (IEMOCAP), MELD etc.