Education & Portfolio

I currently attend Rensselaer Polytechnic Institute (RPI) majoring in mechanical engineering with a minor in music. I am also involved with research on campus involving AAC and AI voice generation. Specifically, I am finding ways to correct AI voice generation to humanely and safely make it sound more like a human and remove its voice disorders (created by the AI training off of data from humans that exhibit voice disorder) and only giving access to that kind of technology to AAC users. While there are ethical concerns with teaching an AI how to properly sing and speak, me and my research group are doing everything we can to limit its reach and to only use it and give it to those that need it the most, AAC users.

AAC users use devices that run a text-to-speech program that communicate for them. However, all of these devices come with the same six (6) standard voices for over 3 million American users to choose from, and many more around the globe. There is a pre-existing solution to our research, of which was covered in a Ted-Ed video. However, the current solution (presented in the Ted-Ed video) is incredibly costly and realistically not an option to very few people. Our goal of our research is to provide a more cost-effective solution by utilizing a better and more ethically sourced and trained AI that is able to realistically and effecively replicate human speach and singing capabilities. We have made great progress on our research, specifically with our main project that showcases our research "The Other Side of Silence." You can find the New York Times article here.