To study effective speech features which can represent different emotion styles in infant voice, nonlinear features based on Teager Energy Operator are investigated. Neutral state and 4 emotional states (i.e. happiness, impatience, anger and fear) are classified from the infant voice database. MFCC extraction and HMM-based emotion classification are used as baseline system to evaluate the emotional classification performance of nonlinear features. In comparison with MFCC, relative improvements which are 2%, 2% , 2% and 10% of classification capacity are obtained when using NFD_Mel , AF_Mel, DAF_Mel and TEO_SBCC. But the performance of emotion classification decreases respectively by 14% for using AM_SBCC.
Emotion Classification of Infant Voice Based on Features Derived from Teager Energy Operator
2008 Congress on Image and Signal Processing ; 5 ; 333-337
2008-05-01
345458 byte
Conference paper
Electronic Resource
English
Radar echo envelope extraction using Teager energy operator and wavelet transform
Tema Archive | 2008
|Research on Motor Bearing Fault Detection Method Based on Teager—Kaiser Energy Operator
British Library Conference Proceedings | 2020
|Research on Motor Bearing Fault Detection Method Based on Teager–Kaiser Energy Operator
Springer Verlag | 2020
|