Software

For September 10

Matt: Keep going, speech recognition, having shimi play a genre/track you request.

Yashveer and Sam:

Consider more what you would be interested in applying to Shimi and do some background research

Two things I'm very interested in but you don't have to be are below. If you have strong alternate ideas that's cool too.

• Audio synthesis with deep learning (I've been doing quite a bit of work in this area so can help - implementing this would be cool https://magenta.tensorflow.org/nsynth-fastgen
• Shimi as a music teacher - recognizing if you sing a wrong note in a scale, etc.. Indefinitely expandable obviously.

For September

Goals:

How you did it:

Results:

What next: