Various signals can be obtained from the body and these signals are mostly used in diagnostic procedures. Where as researchers in MIT have developed a smart watch which analyzes the vital parameters and speech patterns and tell whether the person is happy, sad or normal.
They implemented this on a Samsung Simband– a research friendly wearable. This can be used to develop social communication and will help people with Asperger’s syndrome and autism, etc,.
To analyze speech in real time Researchers Tuka AlHanai and Mohammad Mahdi Ghassemi from MIT have built an algorithm. The process is carried out by telling a happy or sad story then the programmed watch receives the speech patterns and records all the vital parameters such as heart rate, blood pressure, temperature, pulse etc,. When the speech pattern is analyzed the speaker’s tone pitch and vocabulary, According to the obtained speech pattern and parameters the watch tells whether the person is happy or sad in real time.
With 83% accuracy the overall tone of the body and the speech patterns and analysis of physiological signals the result is given.
“As far as we know, this is the first experiment that collects both physical data and speech data in a passive but robust way, even while subjects are having natural, unstructured interactions. Our results show that it’s possible to classify the emotional tone of conversations in real-time,” says Ghassemi, one of the researchers.