Analysis of Speech Features for Emotion Detection: A Review

Emotion detection of speech in human machine interaction is very important. Framework for emotion detection is essential, that includes various modules performing actions like speech to text conversion, feature extraction, feature selection and classification of those features to identify the emotions. The features used for emotion detection of speech are prosody features, spectral features and voice quality features. The classifications of features involve the training of various emotional models to perform the classification appropriately. The features selected to be classified must be salient to detect the emotions correctly. And these features should have to convey the measurable level of emotional modulation.