Dysleducate

Inspiration

We were initially alarmed by the fact that about 5% to 10% of the world's population has dyslexia. These people struggle with reading and memory as it affects a section of their brain that controls these functions. We wanted to do something about this!

What it does

Dysleducate takes speech input based on what the user is reading and it converts it to text which is then compared with the original text that was assigned. It then informs the user how any errors they had so that they are aware of their improvement over time.

How we built it

We used Microsoft Azure's Speech to Text Cognitive Service that allowed us to take the user's audio input and get a text output. We used Python to make calls to this service and used Remi to connect the backend with the frontend.

Challenges we ran into

We chose python right off the bat without really thinking about whether it would work well with the service we wanted to use. Turns out that Microsoft's documentation was in only C# and .NET for this service which made understanding the docs very difficult. Since our team had little to no experience with frontend, we chose React as the framework to use which was another bad choice as connecting it to the python backend would be very difficult. Not only that, the service would often lag and give its output in successive phrases that would eventually form a sentence.

Accomplishments that we're proud of

Using the service successfully and finding a way to connect the backend to the frontend.

What we learned

We learned to use new technologies and the importance of thoroughly planning the project before jumping in head-first.

Built With

• html
• python
• remi