Applications of Speech Analysis in Psychiatry

Abstract

The need for objective measurement in psychiatry has stimulated interest in alternative indicators of the presence and severity of illness. Speech may offer a source of information that bridges the subjective and objective in the assessment of mental disorders. We systematically reviewed the literature for articles exploring speech analysis for psychiatric applications. The utility of speech analysis depends on how accurately speech features represent clinical symptoms within and across disorders. We identified four domains of the application of speech analysis in the literature: diagnostic classification, assessment of illness severity, prediction of onset of illness, and prognosis and treatment outcomes. We discuss the findings in each of these domains, with a focus on how types of speech features characterize different aspects of psychopathology. Models that bring together multiple speech features can distinguish speakers with psychiatric disorders from healthy controls with high accuracy. Differentiating between types of mental disorders and symptom dimensions are more complex problems that expose the transdiagnostic nature of speech features. Convergent progress in speech research and computer sciences opens avenues for implementing speech analysis to enhance objectivity of assessment in clinical practice. Application of speech analysis will need to address issues of ethics and equity, including the potential to perpetuate discriminatory bias through models that learn from clinical assessment data. Methods that mitigate bias are available and should play a key role in the implementation of speech analysis.

Artificial Intelligence: A Game-Changer for Mental Health Care

“…The analysis of speech characteristics such as rhythm, tone and volume, closely linked to an individual's mental state, is another promising application of AI in mental health (10). Monotone speech may be a sign of depression, rapid speech may indicate mania, and disjointed word choice or sentences that do not follow a logical pattern may be linked to schizophrenia.…”

“…When these characteristics are pronounced enough, mental health professionals can pick up on them. Yet humans are not perfect, as they may be distracted and sometimes miss warning signs and subtle speech cues (10). AI algorithms could be trained to detect these signs.…”

“…AI algorithms could be trained to detect these signs. Further, AI and mobile devices could enable mental health professionals to track patients, categorise their mental health status and monitor subtle changes daily (10). As far as we know, several colleagues and large companies like IBM are working in this field (4,10).…”

“…Further, AI and mobile devices could enable mental health professionals to track patients, categorise their mental health status and monitor subtle changes daily (10). As far as we know, several colleagues and large companies like IBM are working in this field (4,10). A speech-based mobile app has recently been designed in the University of Colorado, Boulder that takes patients through a series of repetitive verbal exercises, such as telling a story and answering questions about their emotional and psychological state (4).…”

“…However, the impact of technological devices such as this can be enormous given that many people with mental illness live in remote areas where access to mental health professionals (i.e. psychologists., psychiatrists and psychotherapists) is scarce (10) and that rates of mental health distress (e.g. depression, anxiety) are high in the workplace, with mental distress now accounting for most of the sickness absence in Europe and USA (11).…”