An Artificial Intelligence Approach for Early Identification of Depression Characteristics

Description Depression is one of the most common mental disorders in the world, and causes a significant burden both to the individual and to society. The aim of this study is to use machine learning approaches for early identificaton of depression characteristics based on the spoken language. 
Task In this thesis, the student(s) will analyse the speech related characteristics of depression and implement a robust method to extract this information from audio recordings.
Utilises Deep Spectrum System, auDeep, Recurrent Neural Networks.
Requirements Preliminary knowledge in Machine Learning, Good programming skills (e.g. Python, C++).
Languages English and German.
Supervisor Shahin Amiriparian, M. Sc. (