Identifying Schizophrenia Based on Temporal Parameters in Spontaneous Speech

Schizophrenia is a neurodegenerative disease with spectrum disorder, consisting of groups of different deficits. It is, among other symptoms, characterized by reduced information processing speed and deficits in verbal fluency. In this study we focus on the speech production fluency of patients with schizophrenia compared to healthy controls. Our aim is to show that a temporal speech parameter set consisting of articulation tempo, speech tempo and various pause-related indicators, originally defined for the sake of early detection of various dementia types such as Mild Cognitive Impairment and early Alzheimer's Disease, is able to capture specific differences in the spontaneous speech of the two groups. We tested the applicability of the temporal indicators by machine learning (i.e. by using Support Vector Machines). Our results show that members of the two speaker groups could be identified with classification accuracy scores of between 70 - 80% and F-measure scores between 81% and 87%. Our detailed examination revealed that, among the pause-related temporal parameters, the most useful for distinguishing the two speaker groups were those which took into account both the silent and filled pauses.