An app could soon double up as your digital therapist, with researchers developing a program that could analyze your mood based on the fluctuations in your voice. The program, developed by researchers from the University of Maryland, is based on the premise that certain vocal features change as the patient’s depressive symptoms worsen.

The results of the research will be presented at the 168th meeting of the Acoustical Society of America (ASA), held at the Indianapolis Marriott Downtown Hotel from Oct. 27 to 31.

This program is an effort to develop more effective depression treatments that don’t rely on just patient-reported or clinical analysis of symptoms. While these are effective and important in effective screening and diagnosing severity, there is always a margin for error. Doctors for some time now have been asserting the importance of physiologically based measures of depression.

Speech is a known physiological biomarker for detecting depression. Earlier studies, specifically one in 2007 from an unaffiliated lab, have found differences in pitch, loudness, and clarity in speech in patients before and after treatment.

To further corroborate these studies, acoustician Carol Espy-Wilson and her colleagues revisited the records collected in the previous study to investigate the relationship between depression and speech patterns. The earlier study assessed patients' depression levels each week using the Hamilton Depression Scale (a standard clinical evaluation tool to measure the severity of depression) and then recorded them speaking freely about their day.

The Maryland researchers focused on the data from six patients who in the 2007 study had reported being depressed on some days, and not so depressed on other days, during the course of their six-week therapy. They attempted to correlate the Hamilton score with differences in their speech patterns during these “depressive” days.

When patients' were feeling very depressed, their speech tended to be breathier and slower. The team also found increases in jitter and shimmer, two measures of acoustic disturbance that measure the frequency and amplitude variation of the sound, respectively. Speech high in jitter and shimmer tends to sound hoarse or rough.

The researchers now plan to develop a database containing acoustic profile of depression-typical speech. This they will do by comparing speech patterns of individuals with no known mental illnesses and those with depression. This information could be used by a phone app to analyze and provide feedback based on the person’s acoustic signatures.

Combining technology with medicine is just what is needed to appeal to the teen and young adult population, which sees high rates of depression. Patients will also be able to self-monitor their symptoms and recognize to seek professional help, say the researchers.

But they are still a long way away from a finished product. "We definitely need human factors to develop something that people will use," said Espy-Wilson in a statement. "There's a lot that has to go into making this a useful tool."

Source: Espy-Wilson C. 168th Meeting of the Acoustical Society of America. 2014.