Sign In

Communications of the ACM

ACM TechNews

Listening to Bipolar Disorder: Smartphone App Detects Mood Swings Via Voice Analysis

View as: Print Mobile App Share:
The masks of Comedy and Tragedy symbolize bipolar disorder.

A new smartphone app monitors telephone conversations to detect early signs of mood swings in people with bipolar disorder.

Credit: Wikipedia

University of Michigan researchers have developed a smartphone app that monitors the subtle qualities of a person's voice during normal phone conversations to detect early signs of mood changes in people with bipolar disorder. The researchers hope the app will give people with bipolar disorder an early warning of mood swings.

The system is called PRIORI because the researchers hope it will result in a biological marker to prioritize bipolar disorder care to those who need it most urgently.

"These pilot study results give us preliminary proof of the concept that we can detect mood states in regular phone calls by analyzing broad features and properties of speech, without violating the privacy of those conversations," says University of Michigan researcher Zahi Karam.

The app runs in the smartphone's background and automatically monitors the user's voice patterns during all calls made. During a conversation, the software analyzes the characteristics of each of the sounds made. During testing, the researchers demonstrated their analysis of voice characteristics could detect elevated and depressed moods.

They also say the detection of mood states will improve in the future as the software gets trained based on more conversations and data from more patients.

From University of Michigan News Service
View Full Article


Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account