Emolyzer

Basic interface to demonstrate initial working prototype of Emolyzer

Inspiration

People who suffer from Autism Spectrum Disorder could have trouble picking up on what is considered to be common social cues in conversation. This solution harnesses existing technology to put together what can eventually be an app to indicate in real time the general tone of the other person, so that people with ASD can enjoy social interactions as much as the rest of us.

What it does

Emolyzer converts a voice recording to text and analyzes that for emotion. It then presents a graphical representation of the distribution of emotions underlying that voice recording (happy, sad, anger, disgust, and fear).

How we built it

Voice to Text - Google's cloud speech API Text Emotion Analysis - IBM Watson's Tone Analyser Basic front end - Kivy and Python

Challenges we ran into

Installation challenges, and primarily finding the right tools for the right jobs

Accomplishments that we're proud of

Building a basic working prototype in less than 12 hours

What we learned

There's always a tool to do what you want, as long as you know how to look for it, and adapt it

What's next for Emolyzer

This is a basic prototype, and can easily be extended to a fully-functioning mobile app which works in real-time (with some effort and more time). It can also be used for text emotion analysis, since interpreting the tone of text messages has long been an issue that technology users have contended with.