MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Institute of Medical Engineering and Science (IMES) have developed a wearable technology that lets one know if a specific conversation impresses your date or bores him/her to death. The device is bestowed with artificial intelligence capable of assessing a person’s speech patterns and vitals. Based on its reading, you will know whether to cut the date short or go in for a night-cap.
AI In The Pocket
“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. 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,” stated Tuka Alhanai, the co-author of a paper regarding the technology. The paper is to be presented in the Association for the Advancement of Artificial Intelligence (AAAI) conference in San Francisco, reported MIT News. The technology is especially helpful for people suffering from conditions such as Asperger’s that is known to make people highly fidgety and stressful.
It is the first program of its kind to collect physiological signals and assess audio and text transcriptions during an ongoing conversation. While conducting its assessment, it takes care not to interrupt or hamper the natural flow of anyone’s speech. It is similar to a passive observer. Lastly, it prepares a feedback, which has been accurate about 83% of the times in the past.
The creators of the technology stated that there are huge scopes for further improvement. This is possible only if all the parties involved in a conversation use this technology via smart watches. This would enable the technology to create more detailed data based on multiple algorithms that it analyzes. “Our results show that it’s possible to classify the emotional tone of conversations in real-time,” said PhD candidate Mohammad Ghassemi, who partnered with Alhanai on the paper.
“Technology could soon feel much more emotionally intelligent, or even ‘emotional’ itself,” said Björn Schuller, professor and chair of Complex and Intelligent Systems at the University of Passau in Germany. But for now, the technology depends on factors such as skin temperature, blood pressure, heart rate, blood flow and movement to makes its assessment, reported Inverse. The speaker’s tone, pitch, energy, and vocabulary also played a considerable role in the success of the technology. By taking all these factors into account, the technology can determine whether a particular conversation is happy/sad, positive/negative/neutral.