About Me

Jayeon Jason Yi is a second-year M.S. student in Electrical & Computer Engineering at the University of Michigan. His research focuses on an intersection of AI and Audio Technology. He wishes to dive further into representation learning for speech and audio, especially few-shot learning of esoteric concepts.

To this end, he reached out to Prof. Minje Kim and was very lucky to be allowed to visit his lab over Fall 2024 to work on DNN-based codecs for speech and audio. Jayeon has also worked on a different DNN-based codec project over Summer 2024 as a Applied Scientist Intern at Amazon.com, Inc. Before this, he worked with Prof. Hun-Seok Kim on a project related to video and image compression. During his Bachelor’s, Jayeon was a student intern at Music and Audio Research Group, Seoul National University, under the guidance of Prof. Kyogu Lee. Projects from this period culminated in works in Speech Declipping and Music-synced game content generation, accepted and presented in an international conferences. For the latter work, he consulted domain experts and has been trying to shape his future research directions (as above) based on the feedbacks he received.

In his free time, he makes music for fun. He has sold/provided a number of songs to games.

Here’s a CV, which includes a list of publications.