The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) contains audio of 24 professional actors (12 female, 12 male), vocalizing two statements in a neutral North American accent. Speech includes calm, happy, sad, angry, fearful, surprise, and disgust expressions, and song contains calm, happy, sad, angry, and fearful emotions. Each expression is produced at two levels of emotional intensity (normal, strong), with an additional neutral expression.
The tasks performed on this dataset are:
Data Understanding & Preparation Outlier detection Imbalanced learning Advanced classification Advanced regression Motif and discord detection Application of explainability methods
Besides some notebook files with the code written for these purposes, a report of the whole project is provided.
Some cells in the notebooks are commented, in order to avoid the related files to be too heavy.