Depression and schizophrenia are reflected in several multimodal biomarkers. It also affects voice, speech, facial movement and body movement. The aim of this topic is to use these biomarkers for automatic disease detection using machine learning and deep learning. The aim is to combine different modalities to increase the efficiency of the learned models. The prjoject is carried out in collaboration with the Department of Psychiatry and Psychotherapy, Semmelweis University. For more information, please contact us in the Informatics building, room B 156, at sztaho.david@vik.bme.hu or Microsoft Teams (Dávid Sztahó, sztaho.david@vik.bme.hu).