Voice acoustic measures of depression severity and treatment response collected via interactive voice response (IVR) technology

Abstract

Efforts to develop more effective depression treatments are limited by assessment methods that rely on patient-reported or clinician judgments of symptom severity. Depression also affects speech. Research suggests several objective voice acoustic measures affected by depression can be obtained reliably over the telephone. Thirty-five physician-referred patients beginning treatment for depression were assessed weekly, using standard depression severity measures, during a six-week observational study. Speech samples were also obtained over the telephone each week using an IVR system to automate data collection. Several voice acoustic measures correlated significantly with depression severity. Patients responding to treatment had significantly greater pitch variability, paused less while speaking, and spoke faster than at baseline. Patients not responding to treatment did not show similar changes. Telephone standardization for obtaining voice data was identified as a critical factor influencing the reliability and quality of speech data. This study replicates and extends previous research with a larger sample of patients assessing clinical change associated with treatment. The feasibility of obtaining voice acoustic measures reflecting depression severity and response to treatment using computer-automated telephone data collection techniques is also established. Insight and guidance for future research needs are also identified.

A comparative study of different classifiers for detecting depression from spontaneous speech

“…Although depressed speech has a monotone characteristic indicated by changes in pitch and formants [4,3,25], their performances here were not as good as expected. That might be an indication that pitch and formants features are more suitable in a speaker-dependent comparison.…”

“…Psychology research of depressed speech found several distinguishable prosodic features, such as differences in the pitch, loudness, speaking rate, and articulation [3]. Moreover, the research found that formants are a feature significantly distinguishing depressed from non-depressed speech [4,5], with a noticeable decrease in the second formant for depressed compared to healthy controls [4].…”

“…Therefore, failure to diagnose depression in primary care is a critical public health problem that results in high societal costs related to disability, morbidity, mortality, and excessive health care utilisation [2]. Moreover, effective depression treatment is limited by current assessment methods that rely almost exclusively on patient-reported or clinical judgements of symptom severity [3], risking a range of subjective biases. We believe that affective sensing technology will play a major role in providing an objective assessment.…”

Eye movement analysis for depression detection

“…Based on the WHO report, the barriers to effective diagnosis of depression include a lack of resources and trained health care providers. Moreover, the assessment methods of diagnosing depression rely almost exclusively on patient-reported or clinical judgments of symptom severity [6], risking a range of subjective biases. Our goal here is to investigate the general characteristics of depression, which we hope will lead to an objective affective sensing system that assists clinicians in their diagnosis and monitoring of clinical depression.…”

“You’re as Sick as You Sound”: Using Computational Approaches for Modeling Speaker State to Gauge Illness and Recovery

“…Mundt et al [40] presented a study in which they elicited, recorded and analyzed speech samples from depressed patients in order to identify voice acoustic patterns associated with depression severity and treatment response. An IVR telephone system was developed by Healthcare Technology Systems (Madison, WI) and used to collect speech samples from 35 patients.…”