Novel Hilbert Energy Spectrum Based Features for Speech Emotion Recognition

In this paper, a novel feature called ECC is proposed via feature extraction of the Hilbert energy spectrum which describes the distribution of the instantaneous energy. The experimental results conspicuously demonstrated that ECC outperforms the traditional short-term average energy. Afterwards, further improvements of ECC were developed. TECC is gained by combining ECC with the Teager energy operator, and EFCC is obtained by introduced the instantaneous frequency to the energy. In the experiments, seven status of emotion were selected to be recognized and the highest 83.57% recognition rate was achieved within the classification accuracy of boredom reached up to 100%. The numerical results indicate that the proposed features ECC, TECC and EFCC can improve the performance of speech emotion recognition substantially.