Speech is the most natural way of expressing ourselves as humans. It is only natural then to extend this communication medium to computer applications. We define speech emotion recognition (SER) systems as a collection of methodologies that process and classify speech signals to detect the embedded emotions.
Dataset: https://opendata.deepsig.io/datasets/2016.10/RML2016.10b.tar.bz2
Different forms of data were used, raw data, derivative of data and integral of data.
4 neural networks models were created, CNN, RNN, LSTM and CONV-LSTM.
(detailed project requirements can be found in PR-assignment 4 pdf)