Emotions play a significant role in human mental life. It is a medium of expression of one’s perspective or one’s mental state to others. This is essential to our rational as well as intelligent decisions. Automatic Speech Emotion recognition has become a promising area of study in the field of human computer interaction. The following paper provides an overview of Speech Emotion Recognition and related work. A comparison study of classifying emotions from speech using various deep learning models (CNN, CNN-Transfer Learning Model, LSTM) is also presented. The datasets used were: RAVDESS, SAVEE, TESS.