Speech Emotion Recognition (SER) - Project aim to recognize emotion through speech. Databases used - Ravdess,Tess & Savee. Feature Extractor used - MFCC, STFT & Chroma, with three different extractor able to recognize emotion with high accuracy.
A speech emotion recognition (SER) system that won 1st place in a competition for a deep learning master-course. It uses a parallel CNN built using Keras and Tensorflow.