Our research focuses on developing machine learning models that learn the relationships between vision and sound. In the first part of our project, we aim to make a model that will predict scene segmentations by listening to stereo audio. In another part of our project, we aim to make a model that separates multiple audio sources in the same video. This work has numerous applications that range from improving audio smart devices to enhancing recorded videos.

Through this SuperUROP, I aim to have a quality research experience combining my passions for computer science and audio technology. I will apply the skills I have learned from courses in machine learning, signals and systems, and music technology. I am interested in pursuing a graduate degree in computer science and I hope to use this experience to refine my research interests and develop relationships in the research community.