What it does

User reads a word into the microphone and the application returns a feedback to how close the user speaks to the word they read

How we built it

We started off the project by building webpages with Django. We utilized Bootstrap to add style for any screen size. Used Allosaurus as a python model that contains pre trained models that determined the phonetics by listening to a .wav file

Challenges we ran into

Finding a way to compare the user's input to the correct phonetics of the word given to them.
Python pyAudio wouldn't install due to a missing system header file that was clearly there.

Accomplishments that we're proud of

Understanding how Django deals with URLs and routing.
Having setup a log in

What we learned

Learned how phonetics work. Learned how the DOM works.
The intricacies of the back end and the front end. How to implement voice to speech in Python

What's next for Right Speech

Use computer vision by looking at the users mouth movement and comparing it to references that has the correct mouth movement.

Share this project: