A novel method design for diagnosis of psychological symptoms of depression using speech analysis

Clinical depression can be characterized by a range of psychological factors, resulting in social, occupational and educational impaired function. Current clinical practice depends almost exclusively on self-report and clinical opinion, risking a range of subjective biases. Such methods are subjective and single in nature, and lack an objective predictor of depression. This project aims at developing a novel method for diagnosis of depression using speech analysis from psychological perspective. It is well known that the Self is not only the cognitive subject, but also the core of personality. In this PhD work, for above reason, classical scientific psychology paradigms are employed on abnormalities of self-related processing in patients from different dimensions of the Self, and speech signal processing methods and Machine Learning methods are adopted for depressed speech. We believe the method can better capture psychological characteristics of depressed patients, and make a meaningful progress in improving diagnosis accuracy.