Inspiration
Being a group of music enthusiasts that all play a different instrument, we always tried to play music together. Keyword: tried. We realized that this was not as simple as it sounds, since not all instruments play in the same key (flutes/piano in C, clarinets in Bb, Horns in F, etc.). Therefore, it was difficult for us to find music that all matched the key our instruments were in. We wanted to make something that makes it easy for musicians in different keys to make music together!
What it does
The Transposer uses images of music notes, and returns what note they are originally and the transposed note, both in letter notations. Currently, the Transposer is defaulted to transposing by one, but in the future, the implementation would include an user input to transpose to whatever degree they would like.
How we built it
We built it using Python and Machine Learning. We used image recognition for the music note identification.
Challenges we ran into
One of the biggest challenges we ran into was that we needed to make our own dataset of notes to train the machine learning algorithm with.
Accomplishments that we're proud of
Given that our team consisted of members being 12 hours apart and on the opposite side of the globe, we are proud that we were able to work well together and coordinate meeting times, despite how late or early they were at. Most of our team was also very new to image recognition and had to learn as we went along with the project. We were all able to learn valuable skills, and our skills complemented each other's skills to create the Transposer.
What we learned
We learned that working on coding the same file is difficult when we are not physically near each other and requires a lot of planning.
What's next for Transposer
We would love for the Transposer to then also print out the music notes for the transposed music in the future for musicians that find it easier to read music than read the letter notations.
Log in or sign up for Devpost to join the conversation.