Suche

A Speech-Based Approach for Recognising the Signs of Bipolar Disorder


Description Bipolar disorder is a serious brain illness and one of the main mood disorders that threatens mental well-being. It is one of the well-researched conditions in the field of psychiatry. An important symptom of bipolar disorder is pressured speech which we want to address in this work. 
Task In this thesis, the student(s) will be investigating the feasibility of various deep learning approaches for a speech-based recognition of bipolar disorder.
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. (shahin.amiriparian@informatik.uni-augsburg.de)