New research published in BMC Psychiatry finds that changes in speech such as speed, pitch, number of pauses, and intensity may predict who may report more depressive symptoms. The research team found that they could predict with 93% accuracy who would have scores on a measure of depression high enough to be clinically significant. This research may lead to new early screening methods for depression.
Major depressive disorder is one of the most common mental illnesses of our time; it occurs all over the world and affects more than 264 million people, according to the WHO. A disease that affects so many could benefit from early detection methods. Research has shown that if early signs of depression are noticed, therapeutic interventions can reduce the intensity of the depressive episode. Alexandra König and colleagues recognize the need for objective and user-friendly early identification tools.
It has long been known that depressed people talk differently; speed, fluency, and pitch are known to change during depressive episodes. Clinicians report looking for these speech features during the diagnosis process. If so, König and the research team were curious to see if a speech analysis test could be developed to detect speech differences in people at risk of depression.
To determine if this was possible, subjects with no clinical diagnosis were used in the hope that some would have more depressive symptoms and would be identified through speech analysis. One hundred and eighteen university students were recruited for the study. First, the participants completed an assessment called ‘Trail Making’. This assessment was designed to measure their cognitive speed in solving problems. Then they took an assessment of depressive symptoms; then they were recorded as they spoke.
The speech task asked them to speak for one minute about something positive in their lives and one minute about something negative. The speech task was analyzed looking at specific acoustic features, how many words were said, and how many words were said in a speech segment (before a pause).
Their results showed that 25 of their subjects scored high enough on the measure of depression to qualify for a clinical diagnosis of depression. These 25 subjects spoke more words than those who did not score high on depression, and this was true for both the positive and negative stories. In addition, speech rate, pitch, and prosodic features of speech were excellent predictors of who would have depression scores. Finally, those with high depression scores took longer to complete the Trail Making Test.
The research team acknowledges some limitations of their work. Their voice recording was short, just two minutes per subject, which may have taken longer to make reliable predictions. Second, the subjects of their study were all university students, making the sample unrepresentative. Finally, the subjects were not observed clinically, so it is impossible to know if they would have been diagnosed with clinical depression.
Despite these limitations, the research team finds their work valuable in pursuing early detection of depressive symptoms. They conclude: “Taken together, our study adds to the current literature that speech features are sensitive to the detection of depressive symptoms, even in a non-clinical sample.”
The study, “Detecting subtle signs of depression with automated speech analysis in a non-clinical sample,” is authored by Alexandra König, Johannes Tröger, Elisa Mallick, Mario Mina, Nicklas Linz, Carole Wagnon, Julia Karbach, Caroline Kuhn, and Jessica Peter.