AN EMOTION RECOGNITION BASED BODY AND MIND TRAINING APPLICATION USING RNN ALGORITHMS
The main objective of the proposed system is to recognize emotions through speech using Recurrent Neural Networks and suggest physical exercises accordingly for the beneficiary of people who prefer to choose a balanced life style in an efficient way. Recurrent neural network (RNN) classifier is used to classify the emotions like happiness, fear, sadness, disgust, anger and surprise. The outcome for multiples combination of the features and on similar databases are compared and explained. The overall experimental results would reveal that the feature combination has the highest accuracy rate on emotional databases using RNN classifier. Many researchers have used different classifiers for human emotion recognition and classification from speech such as Hidden Markov Model (HMM), Bayes classifier (MLBC), Gaussian Mixture Model (GMM), Kernel deterioration and K-nearest Neighbors approach (KNN), support vector machine (SVM), Naive Bayes classifier, etc,.The main disadvantage is that only single input and corresponding output is given and combinations of output is a tough task and the algorithm gets costly. Our proposed system is used to suggest the physical exercise from speech. In recent research, many common features are extracted, such as energy, pitch, format, and some spectrum features such as Mel-Frequency Cestrum Coefficients (MFCC) and Modulation spectral features. In this work, Modulation spectral features will be used, to extract the emotional features. Speech samples from Standard English emotional database are used in analyzing, recognition and classification of emotions from audio samples. This project will be helpful to people who need guidance in recognizing their emotion and to get a better physical exercise suggestion.