Author : Jagruti Dambre and Jayshree Pansare

Depression is a major mental health disease of human which is rapidly affecting lives worldwide. The vocal and visual feature provide useful information to treat depression. It shows the manifestation resembles absence of interest with exercises, the constant sentiment of bitterness. Significant depression can bring about a determination of social and physical side effects. It could remember changes in rest, craving, vitality level, concentration, day by day conduct or confidence. Depression are regularly identified with thoughts of suicide. In recent years, deep-learned applications concentrated on neural networks have shown superior performance at hand-crafted apps in various areas. Deep-learned apps that settle the above issues that may precisely assess the degree of voice and face depression. In the proposed method, Convolutionary Neural Networks (CNN) is first developed for learning deep-learned features and descriptive raw waveforms for visual expressions. Second, The MFCC technique is used for vocal data processing. It is most commonly used in speaker recognition for audio features. The work includes combined fine-tuning layers to fuse the CNN raw and spectrogram to enhance depression detection efficiency to capture the complementary details within the deep-learned functionalities. This depression detection technique is reliable and efficient.

Keywords: Depression detection,  deep learning, visual expression, vocal expression