Hi, I'm Darius!
I am a PhD Candidate in Intelligent Systems Engineering and Computer Science at Indiana University,
advised by Dr. Minje Kim.
My research primarily focuses on audio and speech source separation and
neural audio coding, with additional work in classification, automatic speech recognition (ASR), and
generative models. I have published my work in venues such as ICASSP, WASPAA, and ISMIR,
and was honored to receive a best paper award
for our research on hyperbolic audio embeddings. Additionally, I hold multiple U.S. patents.
Previously, I worked as a full-time engineer for the Apple Music Apps Team (Logic Pro, GarageBand)
and conducted research at Mitsubishi Electrical Laboratories (MERL) and Google Research.
Currently, I am interning at Netflix as an ML Research Intern, focusing on multi-modal generative problems.
I will be graduating later this year and am actively seeking full-time opportunities in the industry. Please feel free to reach-out if you have opportunities that align with my background; I would love to discuss further!