I graduated from Princeton University in 2018 with a B.S.E. degree in Electrical Engineering and certificates in Appications of Computing, Engineering Managament Systems and Musical Performance in Conducting. Before that, I graduated as the valedictorian of the Class of 2014 from Central Valley High School. Within the Electrical Engineering Department at Princeton University, I concentrated in the Data and Information track.
The senior thesis is an important part of the Princeton undergraduate experience. I combined my passion for music and software engineering in my thesis, "Deconstructing Mozart: A GAN-Style Approach to Raw Audio Processing and Generation", with Professor Niraj Jha as my advisor and Ozge Akmandor as my research associate.
Abstract: We propose a new system for raw audio processing and generation which combines the success of Generative Adversarial Networks (GANs) and WaveNet, a generative model created by DeepMind. This system will generate piano music using only sample piano audio les that are given to it. The use of GANs together with raw audio, rather than derived features, makes this project unique in the realm of machine learning. Most previous works that compose music through artificial means utilize representations of music, rather than raw audio, due to computational complexity, and previous works that use GANs often solve the problem of image synthesis. Current progress of the fully implemented system with WaveNet and GANs are able to nearly mimic the frequency domain characteristics of the inputted data.
Read the full text here.