Speech Emotion Recognition using MFCC features and LSTM network

Speech is a commonly used signal for interaction between humans, this leads to the usage of speech for human and machine interactions as well. Improvements in this interactive system reach toward speech emotion recognition (SER) system. SER gives sufficient intelligence for efficient natural communication between humans and machines. SER system classifies emotional states such as sadness, angry, neutral, and happiness from the speaker's utterances. This paper describes speech features and machine learning models that can be used for SER. For effective classification and to learn multidimensional complex data, a deep learning algorithm is used in this system. This paper also presents the preliminary results of a system with an MFCC feature and an LSTM algorithm.