This repository contains some of the work developed during my software engineering master's. Initially for a research grant, and later for my dissertation as well.
The area of this work is Speech Emotion Recognition (SER). If you intend to develop something in this area, I advise you to go through my dissertation and some presentations present in the folder Thesis_Mario_Silva
, to have an overview of what this repository contains, as the process of tackling SER problems, from start to finish, is present within this repository.
Also, from this thesis a set of SER Tools was developed, such as machine learning models and an audio pipeline to process audio, online or offline time, to be used for SER classifications.