The recognition of emotions is a vast significance and a high developing field of research in the recent years. The applications of emotion recognition have left an exceptional mark in various fields including education and research. Traditionally, in Speech Emotion Recognition, models require a large number of manually engineered features and intermediate representations such as spectrograms for training. For this research paper we’ve studied many research paper which suggested techniques like Multi Perceptron, Two Stream convolutional network, Multi-task learning model, MFCC, SVM, HMM. The perfection of speech emotion recognition greatly depends upon the types of feature used and also on the classifier employed for recognition. The classification performance is based on extracted characteristics. This paper proposes an implementation of deep learning model on raspberry pi to identify emotion from speech using MFCC (Mel-frequency cepstral coefficients) as an extraction feature and LSTM (Long Short Term Memory) as a classifier, as they proposed higher accuracy compared to other techniques. The proposed deep learning model will be implemented on Raspberry Pi to create a standalone Speech Emotion Recognition system.
Index Terms—Speech Emotion Recognition, Deep Learning, CNN, LSTM, RAVDESS