Automatic depression recognition by intelligent speech signal processing: A systematic survey

Depression has become one of the most common mental illnesses in world. For better prediction and diagnosis, methods automatic depression recognition based on speech signal are constantly proposed updated, with a transition from early traditional hand-crafted features to application architectures deep learning. This paper systematically precisely outlines prominent up-to-date research by intelligent processing so far. Furthermore, for acoustic feature extraction, algorithms classification regression, as well end models investigated analysed. Finally, general trends summarised key unresolved issues identified be considered future studies recognition.