Speech emotion recognition with optimized multi-feature stack using deep convolutional neural networks

The human emotion in communication plays a significant role that can influence how the context of the message is perceived by others. Speech emotion recognition (SER) is one of a field study that is very intriguing to explore because human-computer interaction (HCI) related technologies such as virtual assistant that are implemented nowadays rarely considered the emotion contained in the information relayed by human speech. One of the most widely used ways to perform SER is by extracting features of speech such as mel frequency cepstral coefficient (MFCC), mel-spectrogram, spectral contrast, tonnetz, and chromagram from the signal and using a one-dimensional (1D) convolutional neural network (CNN) as a classifier. This study shows the impact of implementing a combination of an optimized multi-feature stack and optimized 1D deep CNN model. The result of the model proposed in this study has an accuracy of 90.10% for classifying 8 different emotions performed on the ryerson audio-visual database of emotional speech and song (RAVDESS) dataset.