Evidence for depression and schizophrenia in speech prosody

Abstract

We developed automatic computational tools for the monitoring of pathological mental states ‐ including characterization, detection, and classification. We show that simple temporal domain features of speech may be used to correctly classify up to 80% of the speakers in a two-way classification task. We further show that some features strongly correlate with certain diagnostic evaluation scales, suggesting the contribution of such acoustic speech properties to the perception of an apparent mental condition.