Abstract |
Speech emotion recognition (SER) plays a significant role in human–machine interaction. Emotion recognition from speech and its precise classification is a challenging task because a machine is unable to understand its context. In this project, a pre-trained network is used to extract features from state-of-the-art speech emotional datasets. A correlation-based feature selection technique is applied to the extracted features to select the most appropriate and discriminative features for SER. Four different machine learning algorithms are used and the experiments are performed for speaker-dependent and speaker-independent SER. |