Filtering by
- Creators: Barrett, The Honors College
- Creators: Holbrook, Amy
The purpose of this project is to create a useful tool for musicians that utilizes the harmonic content of their playing to recommend new, relevant chords to play. This is done by training various Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) on the lead sheets of 100 different jazz standards. A total of 200 unique datasets were produced and tested, resulting in the prediction of nearly 51 million chords. A note-prediction accuracy of 82.1% and a chord-prediction accuracy of 34.5% were achieved across all datasets. Methods of data representation that were rooted in valid music theory frameworks were found to increase the efficacy of harmonic prediction by up to 6%. Optimal LSTM input sizes were also determined for each method of data representation.
Collaborating with others is a crucial part of growing creatively, and gaining perspective. With different artistic mediums like dance, film, music and design, there is a lot artists can learn from one another. Art is also a way to convey important messages that reflect social, political and cultural issues, and artists have become increasingly responsible for presenting these issues in a way that will provoke thought and create change. “Luna” is a series of compositions with a goal of inviting the audience into a different world. The use of sound design and electronic music production paired with piano arrangements creates a vast, sonic landscape, and the titles of each piece are related to space. The live performance of the album also involves dance, which adds another human element to the experience.