Dataset for depression detection from speech emotion recognition

Abstract

The recognition of internal emotional state of a person plays an important role in several human related fields. Emotions constitute an essential part of our existence as it exerts great influence on the physical and mental health of people. Depression is a common mental disorder. Developments in affective sensing technology with focus on acoustic features will potentially bring a change due to depressed patients’ slow, hesitating, monotonous voice as remarkable characteristics. The system is intended for classification of emotions and depression by using speech signals. Both time and frequency domain features will be used in feature vector extraction. In feature extraction, the system will use wavelet transform and MFCC. DenseNet will be used to detect the emotion, classify the type of emotion and then depression. This paper will present about the datasets collected for the system and the experimental results on the dataset using Support Vector Machine.