This repository contains a machine learning project of emotion detection from an audio file. More details on the approach and data can be found in the proposal markdown file.
data folder contains audio files from the Toronto emotional speech set (TESS) by Kate Dupuis, M. Kathleen Pichora-Fuller (accessible at https://tspace.library.utoronto.ca/handle/1807/24487)
self_recorded folder contains recordings done by the author of this repository as additional test data
modelling folder contains preprocessed train and test data