MIT Wearable App Detects Emotion Behind Speech In Real Time! Here's How

Researchers from the Massachusetts Institute of Technology (MIT) has developed a wearable app helps detect the emotion behind a speech. This tech hopes to help people with Asperger's Syndrome.

This "emotion" detecting app built by MIT is integrated into a fitness tracker, reports The Verge. The app collects physical and speech data to evaluate the overall tone of the story and, get this, in real time! Yes, the app all does this in real time.

During the research, the participants were ordered to wear the Samsung Simbad, where the app was installed, and tell a story. The band collected physiological data such as their movement, fluctuation in heart rate, blood pressure, and even the participant's skin temperature and again, all in real time. 

According to New Atlas, the app developed by MIT also captures the audio of a conversation that evaluates the speaker's tone, pitch, energy and vocabulary. This is with the help of a neural network algorithm that processes the disposition of a conversation with the interval of 5 seconds.

The system's artificial intelligence (AI) associated the long pauses and repetitive patterns in the voice with sad stories; while various and lively tones are associated with happy stories. Body language was also incorporated in the results - these were based in the participant's movements, like raising one's hand to their face or increased fiddling, which was connected to sadder stories. The MIT researchers claim that the system identified the overall tone of a given conversation with 83 percent accuracy.

"Imagine if, at the end of a conversation, you could rewind it and see the moments when the people around you felt the most anxious," said Tuka Alhanai, a graduate student, and also part of the MIT research team. Tuka also added "Our work is a step in this direction, suggesting that we may not be that far away from a world where people can have an AI social coach right in their pocket."

Should the product be approved for production, it could greatly help people with conditions like Asperger's or autism. The team also hopes to label more intricate emotions soon.