Researchers at the University of Rochester have developed a mobile app that can detect your emotions based on your voice. The prototype app can achieve an impressive 81% level of accuracy by analyzing up to 12 features of speech, such as pitch and tone. Unlike previous emotion evaluating systems, this app does not actually listen to the words or study gestures:
“We actually used recordings of actors reading out the date of the month – it really doesn’t matter what they say, it’s how they’re saying it that we’re interested in,” said Wendi Heinzelman, professor of electrical and computer engineering.
The technology is “trained” to be user dependent so the accuracy rate drops drastically when used on another speaker. Future applications for psychological research and emotion-dependent devices, like light bulbs and music players, can use this emotional intelligence to respond to each user’s needs.