Trending News

MIT's Wearable AI System Detects Conversation's Emotion, Analyze Physical And Speech Data [VIDEO]

By

MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) researchers have come up a wearable AI system that can detect an emotion while the person is talking. This technology from the Massachusetts Institute of Technology can be utilized to better understand social situations.

Researchers at MIT's CSAIL published a paper describing how the wearable AI system detects the emotion of a conversation by means of an audio and physiological data in order to determine the speaker's tone. A PhD candidate who co-authored the paper, Mohammad Ghassemi, stated that as technology has been connecting individuals, it hasn't done that much to enhance those communications, according to Newsweek.

Ghassemi also stated that this new technology by the MIT's CSAIL researchers can help people with conditions, such as Asperger's, to understand which moments in a social interaction led to positive or negative outcomes. Technically, MIT's wearable AI system could be used by everyone to boost up communication.

Nevertheless, the MIT's CSAIL researchers started with over 500 signals that could potentially indicate how a conversation was going. The signals were ranging from movement, speech patterns, individual word choice, then MIT's wearable AI system sort out which of the conversation was most important, rather than dictated by preconceptions, Wired reported.

In spite of that, the research is an ongoing effort from MIT's CSAIL researchers to study emotion detection. But, MIT graduate student Tuka Alhanai, stated that their next step is to improve the emotional granularity of the algorithm, so it can accurately detect boring, excited moments and tense. Alhanai also said that in developing a technology that takes the pulse of human emotions has the potential to improve how human individuals communicate with each other.

Meanwhile, Ghassemi stated that with very little structure, the algorithm of MIT's wearable AI system was able to arrive at what they intuitively thought. Although the research may still be some time away, Alhanai and Ghassemi are hopeful that all will come together.

Watch The Video Here:

© 2024 University Herald, All rights reserved. Do not reproduce without permission.
Real Time Analytics