# Deducing the severity of psychiatric symptoms from the human voice

## TL;DR

This paper investigates whether acoustic features of human voice can be used to automatically and objectively grade psychiatric symptom severity, potentially aiding clinical diagnosis and treatment.

## Contribution

It introduces a methodology that uses acoustic data and non-parametric models to predict psychiatric symptom ratings from speech, highlighting the role of articulatory-phonetic units.

## Key findings

- Different speech units capture various symptoms effectively
- Voice-based models can predict symptom severity with promising accuracy
- Methodology can be employed for clinical symptom grading

## Abstract

Psychiatric illnesses are often associated with multiple symptoms, whose severity must be graded for accurate diagnosis and treatment. This grading is usually done by trained clinicians based on human observations and judgments made within doctor-patient sessions. Current research provides sufficient reason to expect that the human voice may carry biomarkers or signatures of many, if not all, these symptoms. Based on this conjecture, we explore the possibility of objectively and automatically grading the symptoms of psychiatric illnesses with reference to various standard psychiatric rating scales. Using acoustic data from several clinician-patient interviews within hospital settings, we use non-parametric models to learn and predict the relations between symptom-ratings and voice. In the process, we show that different articulatory-phonetic units of speech are able to capture the effects of different symptoms differently, and use this to establish a plausible methodology that could be employed for automatically grading psychiatric symptoms for clinical purposes.