Title:  An Analysis of Vocal Acoustics in Aphasia from Multi-label Clinical Data

Committee: 

Dr. Moore, Advisor      

Dr. Davenport, Chair

Dr. Clements

Abstract:

The objective of the proposed research is to investigate and analyze vocal acoustics in aphasia from multi-label clinical data for detection of stress, depression, and emotional state. Assessing stress and depression in persons living with aphasia is a challenging task. Depression diagnosis in this population is often completed through subjective caregiver questionnaires. Stress diagnostic tests have not been modified for language difficulties. This proposed research aims to help identify objective measures of aphasic speech that can be used to predict stress, depression, and/or emotional state in persons with aphasia. The proposed work will expand prior work focused on prediction of affect in aphasic speech, attempt to model co-occurring motor disorders, and ultimately perform cross-database training between aphasia, depression, and dysarthria databases.