This project is emotion recognizer using speech. I converted audio files into image and then classify with CNNs which image belong to which emotion. These images are MEL spectrogram. A MEL spectrogram is a visual way of representing the signal strength, or “loudness”, of a signal over time at various frequencies present in a particular waveform. data_preparation.py create MEL spectrogram and then split them into their emotion folders. This project is based on one dataset named "RAVDESS". IN the future more dataset will be added
This is an example of a spectrogram extracted from an audio.
