Wavelet Packets for Speech Emotion Recognition

Speech Emotion Recognition (SER) is an emerging research area in Human Computer Interaction (HCI) with wide range of applications. This paper proposes the application of Wavelet Packet Features (WPF) for Speech emotion Recognition. Daubechies wavelets are used in this work. An emotional speech database consisting of nine emotions is created for this experiment. Extreme Learning Machine (ELM) is used as the pattern classifier. We could achieve an overall recognition accuracy of 76.66 % from this experiment.