Benjamin Joseph L. Herrera
Hometown: Phoenix, Arizona, United States
Graduation date: Spring 2025
FURI | Spring 2022
VivyNet: A New Approach to Creating AI-Generated MusicAdvances in machine learning (ML) have allowed researchers to simulate human behaviors. One such behavior is content generation. This field of artificial media creation is difficult to perfect as there are multiple ways an ML model can perform poorly. This difficulty affects the quality of the generated content and does not truly mimic the human nature of the outputted source. This research aims to achieve the following: utilize poems as an input to artificially create classical musical compositions, and research different ways to solve this dilemma by utilizing novel techniques and various ML training methods.
Mentor: Yezhou Yang
Featured project | Spring 2022
Computer science major Benjamin Joseph L. Herrera is working on VivyNet, a tool to allow anyone to create artificial intelligence-generated music from poems, with faculty mentor Assistant Professor Yezhou Yang. He was drawn to the FURI program because of his passion for conducting research.
Why did you choose the project you’re working on in FURI?
I chose this project because it was ambitious and it tested my knowledge about machine learning. Additionally, I am using this project to further understand the current field of machine learning research.
How will your engineering research project impact the world?
This project will allow non-musicians to create their own music from just a small poem. Additionally, it will provide some insight on cross-domain content generation.
What has been your most memorable experience as a student researcher in FURI?
My most memorable moment while in this program was when I got my Optical Music Recognition script to work. This was my “aha!” moment because I had learned how to do threading in Python.
Have there been any surprises in your research?
Yes, in fact, there were many. One such surprise was when I found a website that contained all of the data we needed to create a training dataset.
How do you see this experience helping with your advanced degree goals?
My experience in FURI helped me see the roadblocks and struggles I will be facing when I undergo my master’s and doctoral degrees.
What is the best advice you’ve gotten from your faculty mentor?
The best advice my mentor gave me is to take things slowly and focus on one aspect before moving to the other. This advice allowed me to fully understand what I am doing, which prevented me from aimlessly running into walls I could not jump over.
What other projects are you involved in?
I am also involved in other engineering projects such as Argos Vision, which aims to provide government officials automated camera records for street crossings and intersections.