Speech-based assessment of PTSD in a military population using diverse feature classes

Abstract

There is a critical need for detection and monitoring of Post Traumatic Stress Disorder (PTSD) in both military and civilian populations.  Current diagnosis is based on clinical interviews, but clinicians cannot keep up with the growing need.  We examined the feasibility of using speech for assessment in a military population.  We analyzed recordings of the Clinician-Administered PTSD Scale (CAPS) interview from military personnel diagnosed as PTSD positive versus negative. Three feature types were explored: frame-level spectral features, longer-range prosodic features, and lexical features. Results using gaussian backend, decision tree and neural network classifiers (for spectral and prosodic features) and boosting (for lexical features) showed an accuracy of 77% correct in split-half cross validation experiments, a figure significantly above chance (which was 61.5% for our dataset). Spectral and prosodic features outperformed lexical features, and feature combination yielded further gains.  An important finding was that sparser prosodic features offered more robustness than acoustic features to channel-based variation in the interview recordings.  Implications and future work are discussed.