PEOPLE with anxiety, depression or stress are often asked to record their mood changes throughout the day, helping psychologists fine-tune their treatment. But they often forget, recording only sparse information at best. Now an emotion-sensing smartphone app that automatically generates someone’s “mood diary” could give psychologists all the data they need.
It’s the brainchild of Matt Dobson and Duncan Barclay, founders of speech recognition firm EI Technologies, based in Saffron Walden, UK. Instead of relying on people writing diaries, the app, called Xpression, listens for telltale changes in a person’s voice that indicate whether they are in one of five emotional states: calm, happy, sad, angry or anxious/frightened. It then lists a person’s moods against the times they change, and automatically emails the list to their psychologist at the end of the day.
To work, the app has to be always on, listening out for the user’s voice once every second, whether they are talking to family, friends, colleagues or even pets. It also listens in on phone calls. If the user is silent, the app does nothing. Crucially for the users’ privacy, it doesn’t record their words, instead seeking out telltale acoustic features â€“ like pitch â€“ that are indicative of emotional state.
This kind of emotion recognition via voice pattern already works well and is a “hot area” of research, says Stephen Cox, head of the speech processing lab at the University of East Anglia in Norwich, UK, who is scientific adviser for the firm.